diff --git a/.buildinfo b/.buildinfo index e1801f3b..055f7d26 100644 --- a/.buildinfo +++ b/.buildinfo @@ -1,4 +1,4 @@ # Sphinx build info version 1 # This file hashes the configuration used when building these files. When it is not found, a full rebuild will be done. -config: 3d61a9c2c162a7ac452c7ec2cbffeab5 +config: 9e28e034788f88155ad752a56985e689 tags: d77d1c0d9ca2f4c8421862c7c5a0d620 diff --git a/404.html b/404.html index e8fdd53e..a34feb5b 100644 --- a/404.html +++ b/404.html @@ -11,7 +11,7 @@ - + 404 - Page Not Found - MO-Gymnasium Documentation @@ -215,6 +215,7 @@
  • Install
  • API
  • Wrappers
    • +
  • Vector Wrappers
  • MORL Baselines

    • Environments

    @@ -234,11 +235,14 @@
  • MO-Mountaincar
  • MO-Mountaincarcontinuous
  • MO-Lunar-Lander
    • +
  • MO-Lunar-Lander-Continuous
  • Miscellaneous @@ -326,9 +330,9 @@
    -

    404 - Page Not Found#

    +

    404 - Page Not Found

    -

    The requested page could not be found.#

    +

    The requested page could not be found.

    @@ -415,8 +419,8 @@

    The requested page could not be found. - + + diff --git a/README/index.html b/README/index.html index e4efb355..7fb6c104 100644 --- a/README/index.html +++ b/README/index.html @@ -11,7 +11,7 @@ - + MO-Gymnasium documentation - MO-Gymnasium Documentation @@ -215,6 +215,7 @@
  • Install
  • API
  • Wrappers
    • +
  • Vector Wrappers
  • MORL Baselines

    • Environments

    @@ -234,11 +235,14 @@
  • MO-Mountaincar
  • MO-Mountaincarcontinuous
  • MO-Lunar-Lander
    • +
  • MO-Lunar-Lander-Continuous

  • Miscellaneous @@ -326,11 +330,11 @@
    -

    MO-Gymnasium documentation#

    +

    MO-Gymnasium documentation

    This folder contains the documentation for MO-Gymnasium.

    For more information about how to contribute to the documentation go to our CONTRIBUTING.md

    -

    Build the Documentation#

    +

    Build the Documentation

    Install the required packages and Gymnasium (or your fork):

    pip install -r docs/requirements.txt
 pip install -e .
@@ -432,8 +436,8 @@ 
    Build the Documentation
-    
+    
+    
     
     
     
diff --git a/_images/minecart-rgb.gif b/_images/minecart-rgb.gif
new file mode 100644
index 00000000..39ad4172
Binary files /dev/null and b/_images/minecart-rgb.gif differ
diff --git a/_images/mo-lunar-lander-continuous.gif b/_images/mo-lunar-lander-continuous.gif
new file mode 100644
index 00000000..2051d754
Binary files /dev/null and b/_images/mo-lunar-lander-continuous.gif differ
diff --git a/_static/basic.css b/_static/basic.css
index 30fee9d0..f316efcb 100644
--- a/_static/basic.css
+++ b/_static/basic.css
@@ -4,7 +4,7 @@
  *
  * Sphinx stylesheet -- basic theme.
  *
- * :copyright: Copyright 2007-2023 by the Sphinx team, see AUTHORS.
+ * :copyright: Copyright 2007-2024 by the Sphinx team, see AUTHORS.
  * :license: BSD, see LICENSE for details.
  *
  */
diff --git a/_static/doctools.js b/_static/doctools.js
index d06a71d7..4d67807d 100644
--- a/_static/doctools.js
+++ b/_static/doctools.js
@@ -4,7 +4,7 @@
  *
  * Base JavaScript utilities for all Sphinx HTML documentation.
  *
- * :copyright: Copyright 2007-2023 by the Sphinx team, see AUTHORS.
+ * :copyright: Copyright 2007-2024 by the Sphinx team, see AUTHORS.
  * :license: BSD, see LICENSE for details.
  *
  */
diff --git a/_static/documentation_options.js b/_static/documentation_options.js
index 6fe7b331..59816731 100644
--- a/_static/documentation_options.js
+++ b/_static/documentation_options.js
@@ -1,5 +1,5 @@
 const DOCUMENTATION_OPTIONS = {
-    VERSION: '1.1.0',
+    VERSION: '1.2.0',
     LANGUAGE: 'en',
     COLLAPSE_INDEX: false,
     BUILDER: 'dirhtml',
diff --git a/_static/language_data.js b/_static/language_data.js
index 250f5665..367b8ed8 100644
--- a/_static/language_data.js
+++ b/_static/language_data.js
@@ -5,7 +5,7 @@
  * This script contains the language-specific data used by searchtools.js,
  * namely the list of stopwords, stemmer, scorer and splitter.
  *
- * :copyright: Copyright 2007-2023 by the Sphinx team, see AUTHORS.
+ * :copyright: Copyright 2007-2024 by the Sphinx team, see AUTHORS.
  * :license: BSD, see LICENSE for details.
  *
  */
@@ -13,7 +13,7 @@
 var stopwords = ["a", "and", "are", "as", "at", "be", "but", "by", "for", "if", "in", "into", "is", "it", "near", "no", "not", "of", "on", "or", "such", "that", "the", "their", "then", "there", "these", "they", "this", "to", "was", "will", "with"];
 
 
-/* Non-minified version is copied as a separate JS file, is available */
+/* Non-minified version is copied as a separate JS file, if available */
 
 /**
  * Porter Stemmer
diff --git a/_static/pygments.css b/_static/pygments.css
index c2e07c71..02b4b128 100644
--- a/_static/pygments.css
+++ b/_static/pygments.css
@@ -106,17 +106,17 @@ body[data-theme="dark"] .highlight .cp { color: #ff3a3a; font-weight: bold } /*
 body[data-theme="dark"] .highlight .cpf { color: #ababab; font-style: italic } /* Comment.PreprocFile */
 body[data-theme="dark"] .highlight .c1 { color: #ababab; font-style: italic } /* Comment.Single */
 body[data-theme="dark"] .highlight .cs { color: #e50808; font-weight: bold; background-color: #520000 } /* Comment.Special */
-body[data-theme="dark"] .highlight .gd { color: #d22323 } /* Generic.Deleted */
+body[data-theme="dark"] .highlight .gd { color: #ff3a3a } /* Generic.Deleted */
 body[data-theme="dark"] .highlight .ge { color: #d0d0d0; font-style: italic } /* Generic.Emph */
 body[data-theme="dark"] .highlight .ges { color: #d0d0d0; font-weight: bold; font-style: italic } /* Generic.EmphStrong */
-body[data-theme="dark"] .highlight .gr { color: #d22323 } /* Generic.Error */
+body[data-theme="dark"] .highlight .gr { color: #ff3a3a } /* Generic.Error */
 body[data-theme="dark"] .highlight .gh { color: #ffffff; font-weight: bold } /* Generic.Heading */
 body[data-theme="dark"] .highlight .gi { color: #589819 } /* Generic.Inserted */
 body[data-theme="dark"] .highlight .go { color: #cccccc } /* Generic.Output */
 body[data-theme="dark"] .highlight .gp { color: #aaaaaa } /* Generic.Prompt */
 body[data-theme="dark"] .highlight .gs { color: #d0d0d0; font-weight: bold } /* Generic.Strong */
 body[data-theme="dark"] .highlight .gu { color: #ffffff; text-decoration: underline } /* Generic.Subheading */
-body[data-theme="dark"] .highlight .gt { color: #d22323 } /* Generic.Traceback */
+body[data-theme="dark"] .highlight .gt { color: #ff3a3a } /* Generic.Traceback */
 body[data-theme="dark"] .highlight .kc { color: #6ebf26; font-weight: bold } /* Keyword.Constant */
 body[data-theme="dark"] .highlight .kd { color: #6ebf26; font-weight: bold } /* Keyword.Declaration */
 body[data-theme="dark"] .highlight .kn { color: #6ebf26; font-weight: bold } /* Keyword.Namespace */
@@ -192,17 +192,17 @@ body:not([data-theme="light"]) .highlight .cp { color: #ff3a3a; font-weight: bol
 body:not([data-theme="light"]) .highlight .cpf { color: #ababab; font-style: italic } /* Comment.PreprocFile */
 body:not([data-theme="light"]) .highlight .c1 { color: #ababab; font-style: italic } /* Comment.Single */
 body:not([data-theme="light"]) .highlight .cs { color: #e50808; font-weight: bold; background-color: #520000 } /* Comment.Special */
-body:not([data-theme="light"]) .highlight .gd { color: #d22323 } /* Generic.Deleted */
+body:not([data-theme="light"]) .highlight .gd { color: #ff3a3a } /* Generic.Deleted */
 body:not([data-theme="light"]) .highlight .ge { color: #d0d0d0; font-style: italic } /* Generic.Emph */
 body:not([data-theme="light"]) .highlight .ges { color: #d0d0d0; font-weight: bold; font-style: italic } /* Generic.EmphStrong */
-body:not([data-theme="light"]) .highlight .gr { color: #d22323 } /* Generic.Error */
+body:not([data-theme="light"]) .highlight .gr { color: #ff3a3a } /* Generic.Error */
 body:not([data-theme="light"]) .highlight .gh { color: #ffffff; font-weight: bold } /* Generic.Heading */
 body:not([data-theme="light"]) .highlight .gi { color: #589819 } /* Generic.Inserted */
 body:not([data-theme="light"]) .highlight .go { color: #cccccc } /* Generic.Output */
 body:not([data-theme="light"]) .highlight .gp { color: #aaaaaa } /* Generic.Prompt */
 body:not([data-theme="light"]) .highlight .gs { color: #d0d0d0; font-weight: bold } /* Generic.Strong */
 body:not([data-theme="light"]) .highlight .gu { color: #ffffff; text-decoration: underline } /* Generic.Subheading */
-body:not([data-theme="light"]) .highlight .gt { color: #d22323 } /* Generic.Traceback */
+body:not([data-theme="light"]) .highlight .gt { color: #ff3a3a } /* Generic.Traceback */
 body:not([data-theme="light"]) .highlight .kc { color: #6ebf26; font-weight: bold } /* Keyword.Constant */
 body:not([data-theme="light"]) .highlight .kd { color: #6ebf26; font-weight: bold } /* Keyword.Declaration */
 body:not([data-theme="light"]) .highlight .kn { color: #6ebf26; font-weight: bold } /* Keyword.Namespace */
diff --git a/_static/searchtools.js b/_static/searchtools.js
index 7918c3fa..b08d58c9 100644
--- a/_static/searchtools.js
+++ b/_static/searchtools.js
@@ -4,7 +4,7 @@
  *
  * Sphinx JavaScript utilities for the full-text search.
  *
- * :copyright: Copyright 2007-2023 by the Sphinx team, see AUTHORS.
+ * :copyright: Copyright 2007-2024 by the Sphinx team, see AUTHORS.
  * :license: BSD, see LICENSE for details.
  *
  */
@@ -99,7 +99,7 @@ const _displayItem = (item, searchTerms, highlightTerms) => {
       .then((data) => {
         if (data)
           listItem.appendChild(
-            Search.makeSearchSummary(data, searchTerms)
+            Search.makeSearchSummary(data, searchTerms, anchor)
           );
         // highlight search terms in the summary
         if (SPHINX_HIGHLIGHT_ENABLED)  // set in sphinx_highlight.js
@@ -116,8 +116,8 @@ const _finishSearch = (resultCount) => {
     );
   else
     Search.status.innerText = _(
-      `Search finished, found ${resultCount} page(s) matching the search query.`
-    );
+      "Search finished, found ${resultCount} page(s) matching the search query."
+    ).replace('${resultCount}', resultCount);
 };
 const _displayNextItem = (
   results,
@@ -137,6 +137,22 @@ const _displayNextItem = (
   // search finished, update title and status message
   else _finishSearch(resultCount);
 };
+// Helper function used by query() to order search results.
+// Each input is an array of [docname, title, anchor, descr, score, filename].
+// Order the results by score (in opposite order of appearance, since the
+// `_displayNextItem` function uses pop() to retrieve items) and then alphabetically.
+const _orderResultsByScoreThenName = (a, b) => {
+  const leftScore = a[4];
+  const rightScore = b[4];
+  if (leftScore === rightScore) {
+    // same score: sort alphabetically
+    const leftTitle = a[1].toLowerCase();
+    const rightTitle = b[1].toLowerCase();
+    if (leftTitle === rightTitle) return 0;
+    return leftTitle > rightTitle ? -1 : 1; // inverted is intentional
+  }
+  return leftScore > rightScore ? 1 : -1;
+};
 
 /**
  * Default splitQuery function. Can be overridden in ``sphinx.search`` with a
@@ -160,13 +176,26 @@ const Search = {
   _queued_query: null,
   _pulse_status: -1,
 
-  htmlToText: (htmlString) => {
+  htmlToText: (htmlString, anchor) => {
     const htmlElement = new DOMParser().parseFromString(htmlString, 'text/html');
-    htmlElement.querySelectorAll(".headerlink").forEach((el) => { el.remove() });
+    for (const removalQuery of [".headerlink", "script", "style"]) {
+      htmlElement.querySelectorAll(removalQuery).forEach((el) => { el.remove() });
+    }
+    if (anchor) {
+      const anchorContent = htmlElement.querySelector(`[role="main"] ${anchor}`);
+      if (anchorContent) return anchorContent.textContent;
+
+      console.warn(
+        `Anchored content block not found. Sphinx search tries to obtain it via DOM query '[role=main] ${anchor}'. Check your theme or template.`
+      );
+    }
+
+    // if anchor not specified or not found, fall back to main content
     const docContent = htmlElement.querySelector('[role="main"]');
-    if (docContent !== undefined) return docContent.textContent;
+    if (docContent) return docContent.textContent;
+
     console.warn(
-      "Content block not found. Sphinx search tries to obtain it via '[role=main]'. Could you check your theme or template."
+      "Content block not found. Sphinx search tries to obtain it via DOM query '[role=main]'. Check your theme or template."
     );
     return "";
   },
@@ -239,16 +268,7 @@ const Search = {
     else Search.deferQuery(query);
   },
 
-  /**
-   * execute search (requires search index to be loaded)
-   */
-  query: (query) => {
-    const filenames = Search._index.filenames;
-    const docNames = Search._index.docnames;
-    const titles = Search._index.titles;
-    const allTitles = Search._index.alltitles;
-    const indexEntries = Search._index.indexentries;
-
+  _parseQuery: (query) => {
     // stem the search terms and add them to the correct list
     const stemmer = new Stemmer();
     const searchTerms = new Set();
@@ -284,21 +304,38 @@ const Search = {
     // console.info("required: ", [...searchTerms]);
     // console.info("excluded: ", [...excludedTerms]);
 
-    // array of [docname, title, anchor, descr, score, filename]
-    let results = [];
+    return [query, searchTerms, excludedTerms, highlightTerms, objectTerms];
+  },
+
+  /**
+   * execute search (requires search index to be loaded)
+   */
+  _performSearch: (query, searchTerms, excludedTerms, highlightTerms, objectTerms) => {
+    const filenames = Search._index.filenames;
+    const docNames = Search._index.docnames;
+    const titles = Search._index.titles;
+    const allTitles = Search._index.alltitles;
+    const indexEntries = Search._index.indexentries;
+
+    // Collect multiple result groups to be sorted separately and then ordered.
+    // Each is an array of [docname, title, anchor, descr, score, filename].
+    const normalResults = [];
+    const nonMainIndexResults = [];
+
     _removeChildren(document.getElementById("search-progress"));
 
-    const queryLower = query.toLowerCase();
+    const queryLower = query.toLowerCase().trim();
     for (const [title, foundTitles] of Object.entries(allTitles)) {
-      if (title.toLowerCase().includes(queryLower) && (queryLower.length >= title.length/2)) {
+      if (title.toLowerCase().trim().includes(queryLower) && (queryLower.length >= title.length/2)) {
         for (const [file, id] of foundTitles) {
-          let score = Math.round(100 * queryLower.length / title.length)
-          results.push([
+          const score = Math.round(Scorer.title * queryLower.length / title.length);
+          const boost = titles[file] === title ? 1 : 0;  // add a boost for document titles
+          normalResults.push([
             docNames[file],
             titles[file] !== title ? `${titles[file]} > ${title}` : title,
             id !== null ? "#" + id : "",
             null,
-            score,
+            score + boost,
             filenames[file],
           ]);
         }
@@ -308,46 +345,47 @@ const Search = {
     // search for explicit entries in index directives
     for (const [entry, foundEntries] of Object.entries(indexEntries)) {
       if (entry.includes(queryLower) && (queryLower.length >= entry.length/2)) {
-        for (const [file, id] of foundEntries) {
-          let score = Math.round(100 * queryLower.length / entry.length)
-          results.push([
+        for (const [file, id, isMain] of foundEntries) {
+          const score = Math.round(100 * queryLower.length / entry.length);
+          const result = [
             docNames[file],
             titles[file],
             id ? "#" + id : "",
             null,
             score,
             filenames[file],
-          ]);
+          ];
+          if (isMain) {
+            normalResults.push(result);
+          } else {
+            nonMainIndexResults.push(result);
+          }
         }
       }
     }
 
     // lookup as object
     objectTerms.forEach((term) =>
-      results.push(...Search.performObjectSearch(term, objectTerms))
+      normalResults.push(...Search.performObjectSearch(term, objectTerms))
     );
 
     // lookup as search terms in fulltext
-    results.push(...Search.performTermsSearch(searchTerms, excludedTerms));
+    normalResults.push(...Search.performTermsSearch(searchTerms, excludedTerms));
 
     // let the scorer override scores with a custom scoring function
-    if (Scorer.score) results.forEach((item) => (item[4] = Scorer.score(item)));
-
-    // now sort the results by score (in opposite order of appearance, since the
-    // display function below uses pop() to retrieve items) and then
-    // alphabetically
-    results.sort((a, b) => {
-      const leftScore = a[4];
-      const rightScore = b[4];
-      if (leftScore === rightScore) {
-        // same score: sort alphabetically
-        const leftTitle = a[1].toLowerCase();
-        const rightTitle = b[1].toLowerCase();
-        if (leftTitle === rightTitle) return 0;
-        return leftTitle > rightTitle ? -1 : 1; // inverted is intentional
-      }
-      return leftScore > rightScore ? 1 : -1;
-    });
+    if (Scorer.score) {
+      normalResults.forEach((item) => (item[4] = Scorer.score(item)));
+      nonMainIndexResults.forEach((item) => (item[4] = Scorer.score(item)));
+    }
+
+    // Sort each group of results by score and then alphabetically by name.
+    normalResults.sort(_orderResultsByScoreThenName);
+    nonMainIndexResults.sort(_orderResultsByScoreThenName);
+
+    // Combine the result groups in (reverse) order.
+    // Non-main index entries are typically arbitrary cross-references,
+    // so display them after other results.
+    let results = [...nonMainIndexResults, ...normalResults];
 
     // remove duplicate search results
     // note the reversing of results, so that in the case of duplicates, the highest-scoring entry is kept
@@ -361,7 +399,12 @@ const Search = {
       return acc;
     }, []);
 
-    results = results.reverse();
+    return results.reverse();
+  },
+
+  query: (query) => {
+    const [searchQuery, searchTerms, excludedTerms, highlightTerms, objectTerms] = Search._parseQuery(query);
+    const results = Search._performSearch(searchQuery, searchTerms, excludedTerms, highlightTerms, objectTerms);
 
     // for debugging
     //Search.lastresults = results.slice();  // a copy
@@ -466,14 +509,18 @@ const Search = {
       // add support for partial matches
       if (word.length > 2) {
         const escapedWord = _escapeRegExp(word);
-        Object.keys(terms).forEach((term) => {
-          if (term.match(escapedWord) && !terms[word])
-            arr.push({ files: terms[term], score: Scorer.partialTerm });
-        });
-        Object.keys(titleTerms).forEach((term) => {
-          if (term.match(escapedWord) && !titleTerms[word])
-            arr.push({ files: titleTerms[word], score: Scorer.partialTitle });
-        });
+        if (!terms.hasOwnProperty(word)) {
+          Object.keys(terms).forEach((term) => {
+            if (term.match(escapedWord))
+              arr.push({ files: terms[term], score: Scorer.partialTerm });
+          });
+        }
+        if (!titleTerms.hasOwnProperty(word)) {
+          Object.keys(titleTerms).forEach((term) => {
+            if (term.match(escapedWord))
+              arr.push({ files: titleTerms[term], score: Scorer.partialTitle });
+          });
+        }
       }
 
       // no match but word was a required one
@@ -496,9 +543,8 @@ const Search = {
 
       // create the mapping
       files.forEach((file) => {
-        if (fileMap.has(file) && fileMap.get(file).indexOf(word) === -1)
-          fileMap.get(file).push(word);
-        else fileMap.set(file, [word]);
+        if (!fileMap.has(file)) fileMap.set(file, [word]);
+        else if (fileMap.get(file).indexOf(word) === -1) fileMap.get(file).push(word);
       });
     });
 
@@ -549,8 +595,8 @@ const Search = {
    * search summary for a given text. keywords is a list
    * of stemmed words.
    */
-  makeSearchSummary: (htmlText, keywords) => {
-    const text = Search.htmlToText(htmlText);
+  makeSearchSummary: (htmlText, keywords, anchor) => {
+    const text = Search.htmlToText(htmlText, anchor);
     if (text === "") return null;
 
     const textLower = text.toLowerCase();
diff --git a/_static/versioning/versioning_menu.html b/_static/versioning/versioning_menu.html
index 1daf4cef..68109cf8 100644
--- a/_static/versioning/versioning_menu.html
+++ b/_static/versioning/versioning_menu.html
@@ -122,15 +122,33 @@
         });
 
         const sortVersions = (a, b) => {
-            // Alpha versions
-            if (a.includes("a")) return 1;
-            if (b.includes("a")) return -1;
-            if (a.replace("v", "") > b.replace("v", ""))
-                return -1
-            else if (a.replace("v", "") < b.replace("v", ""))
-                return 1
-            else
-                return 0
+            const innerA = a.replace("v", "");
+            const innerB = b.replace("v", "");
+
+            if (innerA.match(/[a-z]/) && !innerB.match(/[a-z]/)) return 1;
+            if (!innerA.match(/[a-z]/) && innerB.match(/[a-z]/)) return -1;
+
+            const splittedInnerA = innerA.split("");
+            const splittedInnerB = innerB.split("");
+
+            while (splittedInnerA.length && splittedInnerB.length) {
+                const charA = splittedInnerA.shift();
+                const charB = splittedInnerB.shift();
+
+                if (charA === charB) continue;
+                else if (charA === ".") return 1;
+                else if (charB === ".") return -1;
+                else if (charA.match(/[0-9]/) && charB.match(/[0-9]/)) {
+                    return Number(charB) - Number(charA);
+                } else {
+                    if (charA < charB) return 1;
+                    else if (charA > charB) return -1;
+                    else return 0;
+                }
+            }
+            if (innerA < innerB) return 1;
+            else if (innerA > innerB) return -1;
+            else return 0;
         }
 
         if ((githubUser !== null && githubUser !== "") || (repo !== null && repo !== "")) {
@@ -204,4 +222,4 @@
             console.error("Invalid versioning configuration");
         }
     
-
    \ No newline at end of file +
    diff --git a/_static/videos/minecart-rgb.gif b/_static/videos/minecart-rgb.gif new file mode 100644 index 00000000..39ad4172 Binary files /dev/null and b/_static/videos/minecart-rgb.gif differ diff --git a/_static/videos/mo-lunar-lander-continuous.gif b/_static/videos/mo-lunar-lander-continuous.gif new file mode 100644 index 00000000..2051d754 Binary files /dev/null and b/_static/videos/mo-lunar-lander-continuous.gif differ diff --git a/citing/citing/index.html b/citing/citing/index.html index 0079bb78..587905c2 100644 --- a/citing/citing/index.html +++ b/citing/citing/index.html @@ -11,7 +11,7 @@ - + <no title> - MO-Gymnasium Documentation @@ -215,6 +215,7 @@
  • Install
  • API
  • Wrappers
    • +
  • Vector Wrappers
  • MORL Baselines

    • Environments

    @@ -234,11 +235,14 @@
  • MO-Mountaincar
  • MO-Mountaincarcontinuous
  • MO-Lunar-Lander
    • +
  • MO-Lunar-Lander-Continuous
  • Miscellaneous @@ -401,8 +405,8 @@ - - + + diff --git a/community/community/index.html b/community/community/index.html index 5ac06a12..c1a5ea80 100644 --- a/community/community/index.html +++ b/community/community/index.html @@ -11,7 +11,7 @@ - + Community - MO-Gymnasium Documentation @@ -215,6 +215,7 @@
  • Install
  • API
  • Wrappers
    • +
  • Vector Wrappers
  • MORL Baselines

    • Environments

    @@ -234,11 +235,14 @@
  • MO-Mountaincar
  • MO-Mountaincarcontinuous
  • MO-Lunar-Lander
    • +
  • MO-Lunar-Lander-Continuous
  • Miscellaneous @@ -326,10 +330,10 @@
    -

    Community#

    +

    Community

    If you want to help us out, reach us, or simply ask questions, you can join the Farama discord server here.

    -

    Acknowledgements#

    +

    Acknowledgements

    Aside from the main contributors, some people have also contributed to the project in various ways. We would like to thank them all for their contributions.

    Environments

    @@ -234,11 +235,14 @@
  • MO-Mountaincar
  • MO-Mountaincarcontinuous
  • MO-Lunar-Lander
    • +
  • MO-Lunar-Lander-Continuous
  • Miscellaneous @@ -317,9 +321,10 @@
    -

    Breakable-Bottles#

    +

    Breakable-Bottles

    -../../_images/breakable-bottles.gif +../../_images/breakable-bottles.gif +
    @@ -333,7 +338,7 @@

    Breakable-Bottles

    - + @@ -351,12 +356,12 @@

    Breakable-Bottles -

    Description#

    +

    Description

    This environment implements the problems UnbreakableBottles and BreakableBottles defined in Section 4.1.2 of the paper Potential-based multiobjective reinforcement learning approaches to low-impact agents for AI safety.

    -

    Action Space#

    +

    Action Space

    The action space is a discrete space with 3 actions:

    • 0: move left

      • @@ -365,17 +370,20 @@

      Action Space -

      Observation Space#

      +

      Observation Space

      The observation space is a dictionary with 4 keys:

      • location: the current location of the agent

      • bottles_carrying: the number of bottles the agent is currently carrying (0, 1 or 2)

        • -

      • bottles_delivered: the number of bottles the agent has delivered (0 or 1)

        • +

      • bottles_delivered: the number of bottles the agent has delivered (0, 1 or 2)

      • bottles_dropped: for each location, a boolean flag indicating if that location currently contains a bottle

      +

      Note that this observation space is different from that listed in the paper above. In the paper, bottles_delivered’s possible values are listed as (0 or 1), +rather than (0, 1 or 2). This is because the paper did not take the terminal state, in which 2 bottles have been delivered, into account when calculating +the observation space. As such, the observation space of this implementation is larger than specified in the paper, having 360 possible states instead of 240.

    -

    Reward Space#

    +

    Reward Space

    The reward space has 3 dimensions:

    • time penalty: -1 for each time step

      • @@ -384,15 +392,15 @@

      Reward Space -

      Starting State#

      +

      Starting State

      The agent starts at location 0, carrying no bottles, having delivered no bottles and having dropped no bottles.

    -

    Episode Termination#

    +

    Episode Termination

    The episode terminates when the agent has delivered 2 bottles.

    -

    Arguments#

    +

    Arguments

    Environments

    @@ -234,11 +235,14 @@
  • MO-Mountaincar
  • MO-Mountaincarcontinuous
  • MO-Lunar-Lander
    • +
  • MO-Lunar-Lander-Continuous
  • Miscellaneous @@ -326,7 +330,7 @@
    -

    Classic Control#

    +

    Classic Control

    Multi-objective versions of classical Gymnasium’s environments.

    • Observation Space

    Dict(‘bottles_carrying’: Discrete(3), ‘bottles_delivered’: Discrete(2), ‘bottles_dropped’: MultiBinary(3), ‘location’: Discrete(5))

    Dict(‘bottles_carrying’: Discrete(3), ‘bottles_delivered’: Discrete(3), ‘bottles_dropped’: MultiBinary(3), ‘location’: Discrete(5))

    Reward Shape

    (3,)
    @@ -343,12 +347,27 @@

    Classic Control[time_penalty, reverse_penalty, forward_penalty]

    - + + + + + + + + + + + + + + + + - + @@ -356,6 +375,9 @@

    Classic ControlPranav Gupta's Dissertation

    +
    @@ -446,8 +468,8 @@

    Classic Control - + + diff --git a/environments/deep-sea-treasure-concave/index.html b/environments/deep-sea-treasure-concave/index.html index 151b812e..b9dc38bd 100644 --- a/environments/deep-sea-treasure-concave/index.html +++ b/environments/deep-sea-treasure-concave/index.html @@ -11,7 +11,7 @@ - + Deep-Sea-Treasure-Concave - MO-Gymnasium Documentation @@ -215,6 +215,7 @@
  • Install
  • API
  • Wrappers
    • +
  • Vector Wrappers
  • MORL Baselines

    • Environments

    @@ -234,11 +235,14 @@
  • MO-Mountaincar
  • MO-Mountaincarcontinuous
  • MO-Lunar-Lander
    • +
  • MO-Lunar-Lander-Continuous
  • Miscellaneous @@ -317,9 +321,10 @@
    -

    Deep-Sea-Treasure-Concave#

    +

    Deep-Sea-Treasure-Concave

    -../../_images/deep-sea-treasure-concave.gif +../../_images/deep-sea-treasure-concave.gif +

    • Classic Mountain Car env, but with extra penalties for the forward and reverse actions. From Vamplew et al. 2011.

    mo-mountaincarcontinuous-v0

    mo-mountaincar-3d-v0 **

    Continuous / Discrete

    [time_penalty, move_penalty, speed_objective]

    The forward and backward penalties have been merged into the move penalty and a speed objective has been introduced which gives the positive reward equivalent to the car’s speed at that time step.*

    mo-mountaincar-timemove-v0 **

    Continuous / Discrete

    [time_penalty, move_penalty]

    Class Mountain Car env but an extra penalty for moving backwards or forwards merged into a move penalty.

    mo-mountaincar-timespeed-v0 **

    Continuous / Discrete

    [time_penalty, speed_objective]

    Class Mountain Car env but an extra positive objective of speed which gives the positive reward equivalent to the car’s speed at that time step.*

    mo-mountaincarcontinuous-v0

    Continuous / Continuous

    [time_penalty, fuel_consumption_penalty]

    Continuous Mountain Car env, but with penalties for fuel consumption.

    mo-lunar-lander-v2

    mo-lunar-lander-v2

    Continuous / Discrete or Continuous

    [landed, shaped_reward, main_engine_fuel, side_engine_fuel]

    MO version of the LunarLander-v2 environment. Objectives defined similarly as in Hung et al. 2022.

    @@ -357,15 +362,15 @@

    Deep-Sea-Treasure-Concave -

    Description#

    +

    Description

    The Deep Sea Treasure environment is classic MORL problem in which the agent controls a submarine in a 2D grid world.

    -

    Observation Space#

    +

    Observation Space

    The observation space is a 2D discrete box with values in [0, 10] for the x and y coordinates of the submarine.

    -

    Action Space#

    +

    Action Space

    The actions is a discrete space where:

    • 0: up

      • @@ -375,7 +380,7 @@

      Action Space -

      Reward Space#

      +

      Reward Space

      The reward is 2-dimensional:

      • time penalty: -1 at each time step

        • @@ -383,22 +388,22 @@

        Reward Space -

        Starting State#

        +

        Starting State

        The starting state is always the same: (0, 0)

    -

    Episode Termination#

    +

    Episode Termination

    The episode terminates when the agent reaches a treasure.

    -

    Arguments#

    +

    Arguments

    • dst_map: the map of the deep sea treasure. Default is the convex map from Yang et al. (2019). To change, use mo_gymnasium.make("DeepSeaTreasure-v0", dst_map=CONCAVE_MAP | MIRRORED_MAP).

    • float_state: if True, the state is a 2D continuous box with values in [0.0, 1.0] for the x and y coordinates of the submarine.

    -

    Credits#

    +

    Credits

    The code was adapted from: Yang’s source. The background art is from https://ansimuz.itch.io/underwater-fantasy-pixel-art-environment. The submarine art was created with the assistance of DALL·E 2.

    @@ -517,8 +522,8 @@

    Credits#< - - + + diff --git a/environments/deep-sea-treasure-mirrored/index.html b/environments/deep-sea-treasure-mirrored/index.html index 26df938a..4ff35b44 100644 --- a/environments/deep-sea-treasure-mirrored/index.html +++ b/environments/deep-sea-treasure-mirrored/index.html @@ -11,7 +11,7 @@ - + Deep-Sea-Treasure-Mirrored - MO-Gymnasium Documentation @@ -215,6 +215,7 @@
  • Install
  • API
  • Wrappers
    • +
  • Vector Wrappers
  • MORL Baselines

    • Environments

    @@ -234,11 +235,14 @@
  • MO-Mountaincar
  • MO-Mountaincarcontinuous
  • MO-Lunar-Lander
    • +
  • MO-Lunar-Lander-Continuous
  • Miscellaneous @@ -317,9 +321,10 @@
    -

    Deep-Sea-Treasure-Mirrored#

    +

    Deep-Sea-Treasure-Mirrored

    -../../_images/deep-sea-treasure-mirrored.gif +../../_images/deep-sea-treasure-mirrored.gif +

    • @@ -357,15 +362,15 @@

    Deep-Sea-Treasure-Mirrored -

    Description#

    +

    Description

    The Deep Sea Treasure environment is classic MORL problem in which the agent controls a submarine in a 2D grid world.

    -

    Observation Space#

    +

    Observation Space

    The observation space is a 2D discrete box with values in [0, 10] for the x and y coordinates of the submarine.

    -

    Action Space#

    +

    Action Space

    The actions is a discrete space where:

    • 0: up

      • @@ -375,7 +380,7 @@

      Action Space -

      Reward Space#

      +

      Reward Space

      The reward is 2-dimensional:

      • time penalty: -1 at each time step

        • @@ -383,22 +388,22 @@

        Reward Space -

        Starting State#

        +

        Starting State

        The starting state is always the same: (0, 0)

    -

    Episode Termination#

    +

    Episode Termination

    The episode terminates when the agent reaches a treasure.

    -

    Arguments#

    +

    Arguments

    • dst_map: the map of the deep sea treasure. Default is the convex map from Yang et al. (2019). To change, use mo_gymnasium.make("DeepSeaTreasure-v0", dst_map=CONCAVE_MAP | MIRRORED_MAP).

    • float_state: if True, the state is a 2D continuous box with values in [0.0, 1.0] for the x and y coordinates of the submarine.

    -

    Credits#

    +

    Credits

    The code was adapted from: Yang’s source. The background art is from https://ansimuz.itch.io/underwater-fantasy-pixel-art-environment. The submarine art was created with the assistance of DALL·E 2.

    @@ -507,8 +512,8 @@

    Credits#< - - + + diff --git a/environments/deep-sea-treasure/index.html b/environments/deep-sea-treasure/index.html index 9a4f7271..37335e52 100644 --- a/environments/deep-sea-treasure/index.html +++ b/environments/deep-sea-treasure/index.html @@ -11,7 +11,7 @@ - + Deep-Sea-Treasure - MO-Gymnasium Documentation @@ -215,6 +215,7 @@
  • Install
  • API
  • Wrappers
    • +
  • Vector Wrappers
  • MORL Baselines

    • Environments

    @@ -234,11 +235,14 @@
  • MO-Mountaincar
  • MO-Mountaincarcontinuous
  • MO-Lunar-Lander
    • +
  • MO-Lunar-Lander-Continuous
  • Miscellaneous @@ -317,9 +321,10 @@
    -

    Deep-Sea-Treasure#

    +

    Deep-Sea-Treasure

    -../../_images/deep-sea-treasure.gif +../../_images/deep-sea-treasure.gif +

    • @@ -357,15 +362,15 @@

    Deep-Sea-Treasure -

    Description#

    +

    Description

    The Deep Sea Treasure environment is classic MORL problem in which the agent controls a submarine in a 2D grid world.

    -

    Observation Space#

    +

    Observation Space

    The observation space is a 2D discrete box with values in [0, 10] for the x and y coordinates of the submarine.

    -

    Action Space#

    +

    Action Space

    The actions is a discrete space where:

    • 0: up

      • @@ -375,7 +380,7 @@

      Action Space -

      Reward Space#

      +

      Reward Space

      The reward is 2-dimensional:

      • time penalty: -1 at each time step

        • @@ -383,22 +388,22 @@

        Reward Space -

        Starting State#

        +

        Starting State

        The starting state is always the same: (0, 0)

    -

    Episode Termination#

    +

    Episode Termination

    The episode terminates when the agent reaches a treasure.

    -

    Arguments#

    +

    Arguments

    • dst_map: the map of the deep sea treasure. Default is the convex map from Yang et al. (2019). To change, use mo_gymnasium.make("DeepSeaTreasure-v0", dst_map=CONCAVE_MAP | MIRRORED_MAP).

    • float_state: if True, the state is a 2D continuous box with values in [0.0, 1.0] for the x and y coordinates of the submarine.

    -

    Credits#

    +

    Credits

    The code was adapted from: Yang’s source. The background art is from https://ansimuz.itch.io/underwater-fantasy-pixel-art-environment. The submarine art was created with the assistance of DALL·E 2.

    @@ -505,8 +510,8 @@

    Credits#< - - + + diff --git a/environments/fishwood/index.html b/environments/fishwood/index.html index 4acbfed0..389cffcf 100644 --- a/environments/fishwood/index.html +++ b/environments/fishwood/index.html @@ -11,7 +11,7 @@ - + Fishwood - MO-Gymnasium Documentation @@ -215,6 +215,7 @@
  • Install
  • API
  • Wrappers
    • +
  • Vector Wrappers
  • MORL Baselines

    • Environments

    @@ -234,11 +235,14 @@
  • MO-Mountaincar
  • MO-Mountaincarcontinuous
  • MO-Lunar-Lander
    • +
  • MO-Lunar-Lander-Continuous
  • Miscellaneous @@ -317,7 +321,7 @@
    -

    Fishwood#

    +

    Fishwood

    • @@ -329,8 +333,14 @@

    Fishwood

    - - + + + + + + + + @@ -348,12 +358,12 @@

    Fishwood

    Action Space

    Discrete(2)

    Observation Space

    Discrete(2)

    Observation Shape

    (1,)

    Observation High

    [1]

    Observation Low

    [0]

    Reward Shape

    (2,)

    -

    Description#

    +

    Description

    The FishWood environment is a simple MORL problem in which the agent controls a fisherman which can either fish or go collect wood. From Multi-objective Reinforcement Learning for the Expected Utility of the Return.

    -

    Observation Space#

    +

    Observation Space

    The observation space is a discrete space with two states:

    • 0: fishing

      • @@ -361,7 +371,7 @@

      Observation Space -

      Action Space#

      +

      Action Space

      The actions is a discrete space where:

      • 0: go fishing

        • @@ -369,7 +379,7 @@

        Action Space -

        Reward Space#

        +

        Reward Space

        The reward is 2-dimensional:

        • 0: +1 if agent is in the woods, with woodproba probability, and 0 otherwise

          • @@ -377,22 +387,22 @@

          Reward Space -

          Starting State#

          +

          Starting State

          Agent starts in the woods

    -

    Termination#

    +

    Termination

    The episode ends after MAX_TS=200 steps

    -

    Arguments#

    +

    Arguments

    • fishproba: probability of catching a fish when fishing

    • woodproba: probability of collecting wood when in the woods

    -

    Credits#

    +

    Credits

    Code provided by Denis Steckelmacher

    @@ -497,8 +507,8 @@

    Credits#< - - + + diff --git a/environments/four-room/index.html b/environments/four-room/index.html index b246ebc8..19e87389 100644 --- a/environments/four-room/index.html +++ b/environments/four-room/index.html @@ -11,7 +11,7 @@ - + Four-Room - MO-Gymnasium Documentation @@ -215,6 +215,7 @@
  • Install
  • API
  • Wrappers
    • +
  • Vector Wrappers
  • MORL Baselines

    • Environments

    @@ -234,11 +235,14 @@
  • MO-Mountaincar
  • MO-Mountaincarcontinuous
  • MO-Lunar-Lander
    • +
  • MO-Lunar-Lander-Continuous

  • Miscellaneous @@ -317,9 +321,10 @@
    -

    Four-Room#

    +

    Four-Room

    -../../_images/four-room.gif +../../_images/four-room.gif +
    @@ -357,25 +362,25 @@

    Four-Room -

    Description#

    +

    Description

    A discretized version of the gridworld environment introduced in [1]. Here, an agent learns to collect shapes with positive reward, while avoid those with negative reward, and then travel to a fixed goal. The gridworld is split into four rooms separated by walls with passage-ways.

    -

    References#

    +

    References

    [1] Barreto, André, et al. “Successor Features for Transfer in Reinforcement Learning.” NIPS. 2017.

    -

    Observation Space#

    +

    Observation Space

    The observation contains the 2D position of the agent in the gridworld, plus a binary vector indicating which items were collected.

    -

    Action Space#

    +

    Action Space

    The action space is discrete with 4 actions: left, up, right, down.

    -

    Reward Space#

    +

    Reward Space

    The reward is a 3-dimensional vector with the following components:

    • +1 if collected a blue square, else 0

      • @@ -384,21 +389,21 @@

      Reward Space -

      Starting State#

      +

      Starting State

      The agent starts in the lower left of the map.

    -

    Episode Termination#

    +

    Episode Termination

    The episode terminates when the agent reaches the goal state, G.

    -

    Arguments#

    +

    Arguments

    • maze: Array containing the gridworld map. See MAZE for an example.

    -

    Credits#

    +

    Credits

    Code adapted from: Mike Gimelfarb’s source.

    @@ -504,8 +509,8 @@

    Credits#< - - + + diff --git a/environments/fruit-tree/index.html b/environments/fruit-tree/index.html index 823036ca..413e6361 100644 --- a/environments/fruit-tree/index.html +++ b/environments/fruit-tree/index.html @@ -11,7 +11,7 @@ - + Fruit-Tree - MO-Gymnasium Documentation @@ -215,6 +215,7 @@
  • Install
  • API
  • Wrappers
    • +
  • Vector Wrappers
  • MORL Baselines

    • Environments

    @@ -234,11 +235,14 @@
  • MO-Mountaincar
  • MO-Mountaincarcontinuous
  • MO-Lunar-Lander
    • +
  • MO-Lunar-Lander-Continuous
  • Miscellaneous @@ -317,9 +321,10 @@
    -

    Fruit-Tree#

    +

    Fruit-Tree

    -../../_images/fruit-tree.gif +../../_images/fruit-tree.gif +

    • @@ -357,28 +362,28 @@

    Fruit-Tree -

    Description#

    +

    Description

    Full binary tree of depth d=5,6 or 7. Every leaf contains a fruit with a value for the nutrients Protein, Carbs, Fats, Vitamins, Minerals and Water. From Yang et al. 2019.

    -

    Observation Space#

    +

    Observation Space

    Discrete space of size 2^d-1, where d is the depth of the tree.

    -

    Action Space#

    +

    Action Space

    The agent can chose to go left or right at every node. The action space is therefore a discrete space of size 2.

    -

    Reward Space#

    +

    Reward Space

    Each leaf node contains a 6-dimensional vector containing the nutrients of the fruit. The agent receives a reward for each nutrient it collects.

    -

    Starting State#

    +

    Starting State

    The agent starts at the root node (0, 0).

    -

    Episode Termination#

    +

    Episode Termination

    The episode terminates when the agent reaches a leaf node.

    @@ -481,8 +486,8 @@

    Episode Termination - + + diff --git a/environments/grid-world/index.html b/environments/grid-world/index.html index c5a08d43..4a1e46d8 100644 --- a/environments/grid-world/index.html +++ b/environments/grid-world/index.html @@ -11,7 +11,7 @@ - + Grid-World - MO-Gymnasium Documentation @@ -215,6 +215,7 @@
  • Install
  • API
  • Wrappers
    • +
  • Vector Wrappers
  • MORL Baselines

    • Environments

    @@ -234,11 +235,14 @@
  • MO-Mountaincar
  • MO-Mountaincarcontinuous
  • MO-Lunar-Lander
    • +
  • MO-Lunar-Lander-Continuous
  • Miscellaneous @@ -326,7 +330,7 @@
    -

    Grid-World#

    +

    Grid-World

    Environments with discrete observation spaces, e.g., grid-worlds.

    • @@ -471,8 +475,8 @@

    Grid-World - + + diff --git a/environments/minecart-deterministic/index.html b/environments/minecart-deterministic/index.html index 12f4babb..4b865583 100644 --- a/environments/minecart-deterministic/index.html +++ b/environments/minecart-deterministic/index.html @@ -8,10 +8,10 @@ - + - + Minecart-Deterministic - MO-Gymnasium Documentation @@ -215,10 +215,11 @@
  • Install
  • API
  • Wrappers
    • +
  • Vector Wrappers
  • MORL Baselines

    • Environments

    -

    @@ -357,12 +362,12 @@

    Minecart-Deterministic
    -

    Description#

    +

    Description

    Agent must collect two types of ores and minimize fuel consumption. From Abels et al. 2019.

    -

    Observation Space#

    +

    Observation Space

    The observation is a 7-dimensional vector containing the following information:

    • 2D position of the cart

      • @@ -373,7 +378,7 @@

      Observation Space -

      Action Space#

      +

      Action Space

      The action space is a discrete space with 6 actions:

      • 0: Mine

        • @@ -385,7 +390,7 @@

        Action Space -

        Reward Space#

        +

        Reward Space

        The reward is a 3D vector:

        • 0: Quantity of the first minerium that was retrieved to the base (sparse)

          • @@ -394,15 +399,15 @@

          Reward Space -

          Starting State#

          +

          Starting State

          The cart starts at the base on the upper left corner of the map.

    -

    Episode Termination#

    +

    Episode Termination

    The episode ends when the cart returns to the base.

    -

    Arguments#

    +

    Arguments

    • render_mode: The render mode to use. Can be “rgb_array” or “human”.

    • image_observation: If True, the observation is a RGB image of the environment.

      • @@ -412,7 +417,7 @@

      Arguments -

      Credits#

      +

      Credits

      The code was refactored from Axel Abels’ source.

    @@ -422,8 +427,30 @@

    Credits#<

    @@ -357,12 +362,12 @@

    Minecart-Rgb -

    Description#

    +

    Description

    Agent must collect two types of ores and minimize fuel consumption. From Abels et al. 2019.

    -

    Observation Space#

    +

    Observation Space

    The observation is a 7-dimensional vector containing the following information:

    • 2D position of the cart

      • @@ -373,7 +378,7 @@

      Observation Space -

      Action Space#

      +

      Action Space

      The action space is a discrete space with 6 actions:

      • 0: Mine

        • @@ -385,7 +390,7 @@

        Action Space -

        Reward Space#

        +

        Reward Space

        The reward is a 3D vector:

        • 0: Quantity of the first minerium that was retrieved to the base (sparse)

          • @@ -394,15 +399,15 @@

          Reward Space -

          Starting State#

          +

          Starting State

          The cart starts at the base on the upper left corner of the map.

    -

    Episode Termination#

    +

    Episode Termination

    The episode ends when the cart returns to the base.

    -

    Arguments#

    +

    Arguments

    • render_mode: The render mode to use. Can be “rgb_array” or “human”.

    • image_observation: If True, the observation is a RGB image of the environment.

      • @@ -412,7 +417,7 @@

      Arguments -

      Credits#

      +

      Credits

      The code was refactored from Axel Abels’ source.

    @@ -423,7 +428,19 @@

    Credits#<
    - + + + + +
    +
    + Previous +
    + +
    Minecart-Deterministic
    + +
    +
    @@ -507,8 +524,8 @@

    Credits#< - - + + diff --git a/environments/minecart/index.html b/environments/minecart/index.html index 7a4a1b91..96e16273 100644 --- a/environments/minecart/index.html +++ b/environments/minecart/index.html @@ -8,10 +8,10 @@ - + - + Minecart - MO-Gymnasium Documentation @@ -215,6 +215,7 @@
  • Install
  • API
  • Wrappers
    • +
  • Vector Wrappers
  • MORL Baselines

    • Environments

    @@ -234,11 +235,14 @@
  • MO-Mountaincar
  • MO-Mountaincarcontinuous
  • MO-Lunar-Lander
    • +
  • MO-Lunar-Lander-Continuous
  • Miscellaneous @@ -317,9 +321,10 @@
    -

    Minecart#

    +

    Minecart

    -../../_images/minecart.gif +../../_images/minecart.gif +

    • @@ -357,12 +362,12 @@

    Minecart

    -

    Description#

    +

    Description

    Agent must collect two types of ores and minimize fuel consumption. From Abels et al. 2019.

    -

    Observation Space#

    +

    Observation Space

    The observation is a 7-dimensional vector containing the following information:

    • 2D position of the cart

      • @@ -373,7 +378,7 @@

      Observation Space -

      Action Space#

      +

      Action Space

      The action space is a discrete space with 6 actions:

      • 0: Mine

        • @@ -385,7 +390,7 @@

        Action Space -

        Reward Space#

        +

        Reward Space

        The reward is a 3D vector:

        • 0: Quantity of the first minerium that was retrieved to the base (sparse)

          • @@ -394,15 +399,15 @@

          Reward Space -

          Starting State#

          +

          Starting State

          The cart starts at the base on the upper left corner of the map.

    -

    Episode Termination#

    +

    Episode Termination

    The episode ends when the cart returns to the base.

    -

    Arguments#

    +

    Arguments

    • render_mode: The render mode to use. Can be “rgb_array” or “human”.

    • image_observation: If True, the observation is a RGB image of the environment.

      • @@ -412,7 +417,7 @@

      Arguments -

      Credits#

      +

      Credits

      The code was refactored from Axel Abels’ source.

    @@ -422,12 +427,12 @@

    Credits#<

  • Miscellaneous @@ -326,7 +330,7 @@
    -

    Miscellaneous#

    +

    Miscellaneous

    MO-Gymnasium also includes other miscellaneous multi-objective environments:

    @@ -381,7 +385,7 @@

    Miscellaneous - + @@ -390,7 +394,7 @@

    MiscellaneousMO-Lunar-Lander +
    MO-Lunar-Lander-Continuous
     @@ -451,8 +455,8 @@

    Miscellaneous - + + diff --git a/environments/mo-ant-2d/index.html b/environments/mo-ant-2d/index.html index b7a49d8b..62116594 100644 --- a/environments/mo-ant-2d/index.html +++ b/environments/mo-ant-2d/index.html @@ -11,7 +11,7 @@ - + MO-Ant-2D - MO-Gymnasium Documentation @@ -215,6 +215,7 @@
  • Install
  • API
  • Wrappers
    • +
  • Vector Wrappers
  • MORL Baselines

    • Environments

    @@ -234,11 +235,14 @@
  • MO-Mountaincar
  • MO-Mountaincarcontinuous
  • MO-Lunar-Lander
    • +
  • MO-Lunar-Lander-Continuous
  • Miscellaneous @@ -317,9 +321,10 @@
    -

    MO-Ant-2D#

    +

    MO-Ant-2D

    -_static/videos/mo-ant-2d.gif +_static/videos/mo-ant-2d.gif +

    • @@ -357,12 +362,15 @@

    MO-Ant-2D -

    Description#

    +

    Description

    Multi-objective version of the AntEnv environment.

    See Gymnasium’s env for more information.

    +

    The original Gymnasium’s ‘Ant-v4’ is recovered by the following linear scalarization:

    +

    env = mo_gym.make(‘mo-ant-v4’, cost_objective=False) +LinearReward(env, weight=np.array([1.0, 0.0]))

    -

    Reward Space#

    +

    Reward Space

    The reward is 2- or 3-dimensional:

    Environments

    @@ -234,11 +235,14 @@
  • MO-Mountaincar
  • MO-Mountaincarcontinuous
  • MO-Lunar-Lander
    • +
  • MO-Lunar-Lander-Continuous
  • Miscellaneous @@ -317,9 +321,10 @@
    -

    MO-Ant#

    +

    MO-Ant

    -../../_images/mo-ant.gif +../../_images/mo-ant.gif +
    • @@ -357,12 +362,15 @@

    MO-Ant#
    -

    Description#

    +

    Description

    Multi-objective version of the AntEnv environment.

    See Gymnasium’s env for more information.

    +

    The original Gymnasium’s ‘Ant-v4’ is recovered by the following linear scalarization:

    +

    env = mo_gym.make(‘mo-ant-v4’, cost_objective=False) +LinearReward(env, weight=np.array([1.0, 0.0]))

    -

    Reward Space#

    +

    Reward Space

    The reward is 2- or 3-dimensional:

    Environments

    @@ -234,11 +235,14 @@
  • MO-Mountaincar
  • MO-Mountaincarcontinuous
  • MO-Lunar-Lander
    • +
  • MO-Lunar-Lander-Continuous
  • Miscellaneous @@ -317,9 +321,10 @@
    -

    MO-Halfcheetah#

    +

    MO-Halfcheetah

    -../../_images/mo-halfcheetah.gif +../../_images/mo-halfcheetah.gif +

    • @@ -357,12 +362,15 @@

    MO-Halfcheetah -

    Description#

    +

    Description

    Multi-objective version of the HalfCheetahEnv environment.

    See Gymnasium’s env for more information.

    +

    The original Gymnasium’s ‘HalfCheetah-v4’ is recovered by the following linear scalarization:

    +

    env = mo_gym.make(‘mo-halfcheetah-v4’) +LinearReward(env, weight=np.array([1.0, 1.0]))

    -

    Reward Space#

    +

    Reward Space

    The reward is 2-dimensional:

    Environments

    @@ -234,11 +235,14 @@
  • MO-Mountaincar
  • MO-Mountaincarcontinuous
  • MO-Lunar-Lander
    • +
  • MO-Lunar-Lander-Continuous
  • Miscellaneous @@ -317,9 +321,10 @@
    -

    MO-Highway-Fast#

    +

    MO-Highway-Fast

    -../../_images/mo-highway-fast.gif +../../_images/mo-highway-fast.gif +
    • @@ -423,8 +428,8 @@

    MO-Highway-Fast - + + diff --git a/environments/mo-highway/index.html b/environments/mo-highway/index.html index 5996b505..19c60fda 100644 --- a/environments/mo-highway/index.html +++ b/environments/mo-highway/index.html @@ -8,10 +8,10 @@ - + - + MO-Highway - MO-Gymnasium Documentation @@ -215,6 +215,7 @@
  • Install
  • API
  • Wrappers
    • +
  • Vector Wrappers
  • MORL Baselines

    • Environments

    @@ -234,11 +235,14 @@
  • MO-Mountaincar
  • MO-Mountaincarcontinuous
  • MO-Lunar-Lander
    • +
  • MO-Lunar-Lander-Continuous
  • Miscellaneous @@ -317,9 +321,10 @@
    -

    MO-Highway#

    +

    MO-Highway

    -../../_images/mo-highway.gif +../../_images/mo-highway.gif +

    • @@ -357,12 +362,12 @@

    MO-Highway -

    Description#

    +

    Description

    Multi-objective version of the HighwayEnv environment.

    See highway-env for more information.

    -

    Reward Space#

    +

    Reward Space

    The reward is 3-dimensional:

    Environments

    @@ -234,11 +235,14 @@
  • MO-Mountaincar
  • MO-Mountaincarcontinuous
  • MO-Lunar-Lander
    • +
  • MO-Lunar-Lander-Continuous
  • Miscellaneous @@ -317,9 +321,10 @@
    -

    MO-Hopper-2D#

    +

    MO-Hopper-2D

    -_static/videos/mo-hopper-2d.gif +_static/videos/mo-hopper-2d.gif +
    • @@ -357,12 +362,15 @@

    MO-Hopper-2D -

    Description#

    +

    Description

    Multi-objective version of the HopperEnv environment.

    See Gymnasium’s env for more information.

    +

    The original Gymnasium’s ‘Hopper-v4’ is recovered by the following linear scalarization:

    +

    env = mo_gym.make(‘mo-hopper-v4’, cost_objective=False) +LinearReward(env, weight=np.array([1.0, 0.0]))

    -

    Reward Space#

    +

    Reward Space

    The reward is 3-dimensional:

    Environments

    @@ -234,11 +235,14 @@
  • MO-Mountaincar
  • MO-Mountaincarcontinuous
  • MO-Lunar-Lander
    • +
  • MO-Lunar-Lander-Continuous
  • Miscellaneous @@ -317,9 +321,10 @@
    -

    MO-Hopper#

    +

    MO-Hopper

    -../../_images/mo-hopper.gif +../../_images/mo-hopper.gif +
    • @@ -357,12 +362,15 @@

    MO-Hopper -

    Description#

    +

    Description

    Multi-objective version of the HopperEnv environment.

    See Gymnasium’s env for more information.

    +

    The original Gymnasium’s ‘Hopper-v4’ is recovered by the following linear scalarization:

    +

    env = mo_gym.make(‘mo-hopper-v4’, cost_objective=False) +LinearReward(env, weight=np.array([1.0, 0.0]))

    -

    Reward Space#

    +

    Reward Space

    The reward is 3-dimensional:

    Environments

    @@ -234,11 +235,14 @@
  • MO-Mountaincar
  • MO-Mountaincarcontinuous
  • MO-Lunar-Lander
    • +
  • MO-Lunar-Lander-Continuous
  • Miscellaneous @@ -317,9 +321,10 @@
    -

    MO-Humanoid#

    +

    MO-Humanoid

    -../../_images/mo-humanoid.gif +../../_images/mo-humanoid.gif +
    • @@ -357,12 +362,12 @@

    MO-Humanoid -

    Description#

    +

    Description

    Multi-objective version of the HumanoidEnv environment.

    See Gymnasium’s env for more information.

    -

    Reward Space#

    +

    Reward Space

    The reward is 2-dimensional:

    Environments

    -
    @@ -336,10 +341,10 @@

    MO-Lunar-Lander-Continuous

    - + - + @@ -351,18 +356,18 @@

    MO-Lunar-Lander-Continuous

    - +

    Observation High

    [1.5 1.5 5. 5. 3.14 5. 1. 1. ]

    [ 2.5 2.5 10. 10. 6.28 10. 1. 1. ]

    Observation Low

    [-1.5 -1.5 -5. -5. -3.14 -5. -0. -0. ]

    [ -2.5 -2.5 -10. -10. -6.28 -10. -0. -0. ]

    Reward Shape

    (4,)

    Import

    mo_gymnasium.make("mo-lunar-lander-continuous-v2")

    mo_gymnasium.make("mo-lunar-lander-continuous-v3")
    -

    Description#

    +

    Description

    Multi-objective version of the LunarLander environment.

    See Gymnasium’s env for more information.

    -

    Reward Space#

    +

    Reward Space

    The reward is 4-dimensional:

    Environments

    @@ -234,11 +235,14 @@
  • MO-Mountaincar
  • MO-Mountaincarcontinuous
  • MO-Lunar-Lander
    • +
  • MO-Lunar-Lander-Continuous
  • Miscellaneous @@ -317,9 +321,10 @@
    -

    MO-Lunar-Lander#

    +

    MO-Lunar-Lander

    -../../_images/mo-lunar-lander.gif +../../_images/mo-lunar-lander.gif +
    @@ -336,10 +341,10 @@

    MO-Lunar-Lander

    - + - + @@ -351,18 +356,18 @@

    MO-Lunar-Lander

    - +

    Observation High

    [1.5 1.5 5. 5. 3.14 5. 1. 1. ]

    [ 2.5 2.5 10. 10. 6.28 10. 1. 1. ]

    Observation Low

    [-1.5 -1.5 -5. -5. -3.14 -5. -0. -0. ]

    [ -2.5 -2.5 -10. -10. -6.28 -10. -0. -0. ]

    Reward Shape

    (4,)

    Import

    mo_gymnasium.make("mo-lunar-lander-v2")

    mo_gymnasium.make("mo-lunar-lander-v3")
    -

    Description#

    +

    Description

    Multi-objective version of the LunarLander environment.

    See Gymnasium’s env for more information.

    -

    Reward Space#

    +

    Reward Space

    The reward is 4-dimensional:

    • 0: -100 if crash, +100 if lands successfully

      • @@ -378,12 +383,12 @@

      Reward Space - +
      Next
      -
      Miscellaneous
      +
      MO-Lunar-Lander-Continuous
      @@ -467,8 +472,8 @@

      Reward Space - + + diff --git a/environments/mo-mountaincar-3d/index.html b/environments/mo-mountaincar-3d/index.html new file mode 100644 index 00000000..35045fa1 --- /dev/null +++ b/environments/mo-mountaincar-3d/index.html @@ -0,0 +1,662 @@ + + + + + + + + + + + + + + + MO-Mountaincar-3D - MO-Gymnasium Documentation + + + + + + + + + +
      +
      +
      + +
      +
      + + + + MO-Gymnasium Documentation + +
      +
      +
      + + +
      +
      +
      +
      + + + + + + + + Contents + + + + + + Menu + + + + + + + + Expand + + + + + + Light mode + + + + + + + + + + + + + + Dark mode + + + + + + + Auto light/dark mode + + + + + + + + + + + + + + + + + +
      + + +
      + + + + + +
      +
      +
      + + + + + Back to top + +
      + +
      + +
      +
      + +
      +

      MO-Mountaincar-3D

      +
      +_static/videos/mo-mountaincar-3d.gif + +
      +
      + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +

      Action Space

      Discrete(3)

      Observation Shape

      (2,)

      Observation High

      [0.6 0.07]

      Observation Low

      [-1.2 -0.07]

      Reward Shape

      (3,)

      Reward High

      [-1. 0. 1.1]

      Reward Low

      [-1. -1. 0.]

      Import

      mo_gymnasium.make("mo-mountaincar-3d-v0")

      +
      +

      A multi-objective version of the MountainCar environment, where the goal is to reach the top of the mountain.

      +

      See Gymnasium’s env for more information.

      +
      +

      Reward space:

      +

      By default, the reward space is a 3D vector containing the time penalty, and penalties for reversing and going forward.

      +
        +

      • time penalty: -1.0 for each time step

        • +

      • reverse penalty: -1.0 for each time step the action is 0 (reverse)

        • +

      • forward penalty: -1.0 for each time step the action is 2 (forward)

        • +
      +

      #Alternatively, the reward can be changed with the following options:

      +
        +

      • add_speed_objective: Add an extra objective corresponding to the speed of the car.

        • +

      • remove_move_penalty: Remove the reverse and forward objectives.

        • +

      • merge_move_penalty: Merge reverse and forward penalties into a single penalty.

        • +
      +
      +
      + +
      +
      +
      + +
      + + +
      +
      +
      +
      + Copyright © 2023 +
      + +
      +
      +
      + + + + + + +
      +
      +
      + +
      +
      + +
      +
      +
      + + + + + + + + + + + + + + + + + \ No newline at end of file diff --git a/environments/mo-mountaincar-timemove/index.html b/environments/mo-mountaincar-timemove/index.html new file mode 100644 index 00000000..8e9b9c9d --- /dev/null +++ b/environments/mo-mountaincar-timemove/index.html @@ -0,0 +1,662 @@ + + + + + + + + + + + + + + + MO-Mountaincar-Timemove - MO-Gymnasium Documentation + + + + + + + + + +
      +
      +
      + +
      +
      + + + + MO-Gymnasium Documentation + +
      +
      +
      + + +
      +
      +
      +
      + + + + + + + + Contents + + + + + + Menu + + + + + + + + Expand + + + + + + Light mode + + + + + + + + + + + + + + Dark mode + + + + + + + Auto light/dark mode + + + + + + + + + + + + + + + + + +
      + + +
      + + + + + +
      +
      +
      + + + + + Back to top + +
      + +
      + +
      +
      + +
      +

      MO-Mountaincar-Timemove

      +
      +_static/videos/mo-mountaincar-timemove.gif + +
      +
      + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +

      Action Space

      Discrete(3)

      Observation Shape

      (2,)

      Observation High

      [0.6 0.07]

      Observation Low

      [-1.2 -0.07]

      Reward Shape

      (2,)

      Reward High

      [-1. 0.]

      Reward Low

      [-1. -1.]

      Import

      mo_gymnasium.make("mo-mountaincar-timemove-v0")

      +
      +

      A multi-objective version of the MountainCar environment, where the goal is to reach the top of the mountain.

      +

      See Gymnasium’s env for more information.

      +
      +

      Reward space:

      +

      By default, the reward space is a 3D vector containing the time penalty, and penalties for reversing and going forward.

      +
        +

      • time penalty: -1.0 for each time step

        • +

      • reverse penalty: -1.0 for each time step the action is 0 (reverse)

        • +

      • forward penalty: -1.0 for each time step the action is 2 (forward)

        • +
      +

      #Alternatively, the reward can be changed with the following options:

      +
        +

      • add_speed_objective: Add an extra objective corresponding to the speed of the car.

        • +

      • remove_move_penalty: Remove the reverse and forward objectives.

        • +

      • merge_move_penalty: Merge reverse and forward penalties into a single penalty.

        • +
      +
      +
      + +
      +
      +
      + +
      + + +
      +
      +
      +
      + Copyright © 2023 +
      + +
      +
      +
      + + + + + + +
      +
      +
      + +
      +
      + +
      +
      +
      + + + + + + + + + + + + + + + + + \ No newline at end of file diff --git a/environments/mo-mountaincar-timespeed/index.html b/environments/mo-mountaincar-timespeed/index.html new file mode 100644 index 00000000..cb088892 --- /dev/null +++ b/environments/mo-mountaincar-timespeed/index.html @@ -0,0 +1,662 @@ + + + + + + + + + + + + + + + MO-Mountaincar-Timespeed - MO-Gymnasium Documentation + + + + + + + + + +
      +
      +
      + +
      +
      + + + + MO-Gymnasium Documentation + +
      +
      +
      + + +
      +
      +
      +
      + + + + + + + + Contents + + + + + + Menu + + + + + + + + Expand + + + + + + Light mode + + + + + + + + + + + + + + Dark mode + + + + + + + Auto light/dark mode + + + + + + + + + + + + + + + + + +
      + + +
      + + + + + +
      +
      +
      + + + + + Back to top + +
      + +
      + +
      +
      + +
      +

      MO-Mountaincar-Timespeed

      +
      +_static/videos/mo-mountaincar-timespeed.gif + +
      +
      + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +

      Action Space

      Discrete(3)

      Observation Shape

      (2,)

      Observation High

      [0.6 0.07]

      Observation Low

      [-1.2 -0.07]

      Reward Shape

      (2,)

      Reward High

      [-1. 1.1]

      Reward Low

      [-1. 0.]

      Import

      mo_gymnasium.make("mo-mountaincar-timespeed-v0")

      +
      +

      A multi-objective version of the MountainCar environment, where the goal is to reach the top of the mountain.

      +

      See Gymnasium’s env for more information.

      +
      +

      Reward space:

      +

      By default, the reward space is a 3D vector containing the time penalty, and penalties for reversing and going forward.

      +
        +

      • time penalty: -1.0 for each time step

        • +

      • reverse penalty: -1.0 for each time step the action is 0 (reverse)

        • +

      • forward penalty: -1.0 for each time step the action is 2 (forward)

        • +
      +

      #Alternatively, the reward can be changed with the following options:

      +
        +

      • add_speed_objective: Add an extra objective corresponding to the speed of the car.

        • +

      • remove_move_penalty: Remove the reverse and forward objectives.

        • +

      • merge_move_penalty: Merge reverse and forward penalties into a single penalty.

        • +
      +
      +
      + +
      +
      +
      + +
      + + +
      +
      +
      +
      + Copyright © 2023 +
      + +
      +
      +
      + + + + + + +
      +
      +
      + +
      +
      + +
      +
      +
      + + + + + + + + + + + + + + + + + \ No newline at end of file diff --git a/environments/mo-mountaincar/index.html b/environments/mo-mountaincar/index.html index ed96e5c4..21fefc46 100644 --- a/environments/mo-mountaincar/index.html +++ b/environments/mo-mountaincar/index.html @@ -11,7 +11,7 @@ - + MO-Mountaincar - MO-Gymnasium Documentation @@ -215,6 +215,7 @@
    • Install
    • API
    • Wrappers
      • +
    • Vector Wrappers
    • MORL Baselines

    Environments

    @@ -234,11 +235,14 @@
  • MO-Mountaincar
  • MO-Mountaincarcontinuous
  • MO-Lunar-Lander
    • +
  • MO-Lunar-Lander-Continuous
  • Miscellaneous @@ -317,9 +321,10 @@
    -

    MO-Mountaincar#

    +

    MO-Mountaincar

    -../../_images/mo-mountaincar.gif +../../_images/mo-mountaincar.gif +
    @@ -359,13 +364,19 @@

    MO-MountaincarGymnasium’s env for more information.

    -

    Reward space:#

    -

    The reward space is a 3D vector containing the time penalty, and penalties for reversing and going forward.

    +

    Reward space:

    +

    By default, the reward space is a 3D vector containing the time penalty, and penalties for reversing and going forward.

    • time penalty: -1.0 for each time step

    • reverse penalty: -1.0 for each time step the action is 0 (reverse)

    • forward penalty: -1.0 for each time step the action is 2 (forward)

    +

    #Alternatively, the reward can be changed with the following options:

    +
      +

    • add_speed_objective: Add an extra objective corresponding to the speed of the car.

      • +

    • remove_move_penalty: Remove the reverse and forward objectives.

      • +

    • merge_move_penalty: Merge reverse and forward penalties into a single penalty.

      • +
    @@ -462,8 +473,8 @@

    Reward space: - + + diff --git a/environments/mo-mountaincarcontinuous/index.html b/environments/mo-mountaincarcontinuous/index.html index 181ab110..0132d200 100644 --- a/environments/mo-mountaincarcontinuous/index.html +++ b/environments/mo-mountaincarcontinuous/index.html @@ -11,7 +11,7 @@ - + MO-Mountaincarcontinuous - MO-Gymnasium Documentation @@ -215,6 +215,7 @@
  • Install
  • API
  • Wrappers
    • +
  • Vector Wrappers
  • MORL Baselines

    • Environments

    @@ -234,11 +235,14 @@
  • MO-Mountaincar
  • MO-Mountaincarcontinuous
  • MO-Lunar-Lander
    • +
  • MO-Lunar-Lander-Continuous
  • Miscellaneous @@ -317,9 +321,10 @@
    -

    MO-Mountaincarcontinuous#

    +

    MO-Mountaincarcontinuous

    -../../_images/mo-mountaincarcontinuous.gif +../../_images/mo-mountaincarcontinuous.gif +

    • @@ -359,7 +364,7 @@

    MO-Mountaincarcontinuoussource for more information.

    -

    Reward space:#

    +

    Reward space:

    The reward space is a 2D vector containing the time penalty and the fuel reward.

    Environments

    @@ -234,11 +235,14 @@
  • MO-Mountaincar
  • MO-Mountaincarcontinuous
  • MO-Lunar-Lander
    • +
  • MO-Lunar-Lander-Continuous
  • Miscellaneous @@ -317,9 +321,10 @@
    -

    MO-Reacher#

    +

    MO-Reacher

    -../../_images/mo-reacher.gif +../../_images/mo-reacher.gif +

    • @@ -357,11 +362,11 @@

    MO-Reacher -

    Description#

    -

    Mujoco version of mo-reacher-v0, based on Reacher-v4 environment.

    +

    Description

    +

    Multi-objective version of the Reacher-v4 environment.

    -

    Observation Space#

    +

    Observation Space

    The observation is 6-dimensional and contains:

    • sin and cos of the angles of the central and elbow joints

      • @@ -369,11 +374,11 @@

      Observation Space -

      Action Space#

      +

      Action Space

      The action space is discrete and contains the 3^2=9 possible actions based on applying positive (+1), negative (-1) or zero (0) torque to each of the two joints.

    -

    Reward Space#

    +

    Reward Space

    The reward is 4-dimensional and is defined based on the distance of the tip of the arm and the four target locations. For each i={1,2,3,4} it is computed as:

        r_i = 1  - 4 * || finger_tip_coord - target_i ||^2
@@ -478,8 +483,8 @@ 
    Reward Space
-    
+    
+    
     
     
     
diff --git a/environments/mo-supermario/index.html b/environments/mo-supermario/index.html
index 5f93b1dc..ea4a18a5 100644
--- a/environments/mo-supermario/index.html
+++ b/environments/mo-supermario/index.html
@@ -11,7 +11,7 @@
 
         
 
-    
+    
         MO-Supermario - MO-Gymnasium Documentation
       
     
@@ -215,6 +215,7 @@
 
  • Install
    • 
 
  • API
    • 
 
  • Wrappers
    • 
+
  • Vector Wrappers
    • 
 
  • MORL Baselines
    • 
 
 
    Environments
    
@@ -234,11 +235,14 @@
 
  • MO-Mountaincar
    • 
 
  • MO-Mountaincarcontinuous
    • 
 
  • MO-Lunar-Lander
    • 
+
  • MO-Lunar-Lander-Continuous
    • 
 
 
 
  • Miscellaneous
@@ -317,9 +321,10 @@
           
    
             
             
    
-
    MO-Supermario#
    
+
    MO-Supermario
    
 
    
-../../_images/mo-supermario.gif
+../../_images/mo-supermario.gif
+
    • @@ -357,12 +362,12 @@

    MO-Supermario -

    Description#

    +

    Description

    Multi-objective version of the SuperMarioBro environment.

    See gym-super-mario-bros for more information.

    -

    Reward Space#

    +

    Reward Space

    The reward is a 5-dimensional vector:

    • 0: How far Mario moved in the x position

      • @@ -373,7 +378,7 @@

      Reward Space -

      Episode Termination#

      +

      Episode Termination

      The episode terminates when Mario dies or reaches the flag.

    @@ -473,8 +478,8 @@

    Episode Termination - + + diff --git a/environments/mo-swimmer/index.html b/environments/mo-swimmer/index.html index 1debafa9..48809779 100644 --- a/environments/mo-swimmer/index.html +++ b/environments/mo-swimmer/index.html @@ -11,7 +11,7 @@ - + MO-Swimmer - MO-Gymnasium Documentation @@ -215,6 +215,7 @@
  • Install
  • API
  • Wrappers
    • +
  • Vector Wrappers
  • MORL Baselines

    • Environments

    @@ -234,11 +235,14 @@
  • MO-Mountaincar
  • MO-Mountaincarcontinuous
  • MO-Lunar-Lander
    • +
  • MO-Lunar-Lander-Continuous
  • Miscellaneous @@ -317,9 +321,10 @@
    -

    MO-Swimmer#

    +

    MO-Swimmer

    -../../_images/mo-swimmer.gif +../../_images/mo-swimmer.gif +

    • @@ -357,12 +362,15 @@

    MO-Swimmer -

    Description#

    +

    Description

    Multi-objective version of the SwimmerEnv environment.

    See Gymnasium’s env for more information.

    +

    The original Gymnasium’s ‘Swimmer-v4’ is recovered by the following linear scalarization:

    +

    env = mo_gym.make(‘mo-swimmer-v4’) +LinearReward(env, weight=np.array([1.0, 1e-4]))

    -

    Reward Space#

    +

    Reward Space

    The reward is 2-dimensional:

    Environments

    @@ -234,11 +235,14 @@
  • MO-Mountaincar
  • MO-Mountaincarcontinuous
  • MO-Lunar-Lander
    • +
  • MO-Lunar-Lander-Continuous
  • Miscellaneous @@ -317,9 +321,10 @@
    -

    MO-Walker2D#

    +

    MO-Walker2D

    -../../_images/mo-walker2d.gif +../../_images/mo-walker2d.gif +
    • @@ -357,12 +362,12 @@

    MO-Walker2D -

    Description#

    +

    Description

    Multi-objective version of the Walker2dEnv environment.

    See Gymnasium’s env for more information.

    -

    Reward Space#

    +

    Reward Space

    The reward is 2-dimensional:

    Environments

    @@ -234,11 +235,14 @@
  • MO-Mountaincar
  • MO-Mountaincarcontinuous
  • MO-Lunar-Lander
    • +
  • MO-Lunar-Lander-Continuous
  • Miscellaneous @@ -326,7 +330,7 @@
    -

    MuJoCo#

    +

    MuJoCo

    Multi-objective versions of Mujoco environments.

    • @@ -466,8 +470,8 @@

    MuJoCo# - + + diff --git a/environments/resource-gathering/index.html b/environments/resource-gathering/index.html index ec85bd29..11289649 100644 --- a/environments/resource-gathering/index.html +++ b/environments/resource-gathering/index.html @@ -11,7 +11,7 @@ - + Resource-Gathering - MO-Gymnasium Documentation @@ -215,6 +215,7 @@
  • Install
  • API
  • Wrappers
    • +
  • Vector Wrappers
  • MORL Baselines

    • Environments

    @@ -234,11 +235,14 @@
  • MO-Mountaincar
  • MO-Mountaincarcontinuous
  • MO-Lunar-Lander
    • +
  • MO-Lunar-Lander-Continuous
  • Miscellaneous @@ -317,9 +321,10 @@
    -

    Resource-Gathering#

    +

    Resource-Gathering

    -../../_images/resource-gathering.gif +../../_images/resource-gathering.gif +

    • @@ -357,12 +362,12 @@

    Resource-Gathering -

    Description#

    +

    Description

    From “Barrett, Leon & Narayanan, Srini. (2008). Learning all optimal policies with multiple criteria. Proceedings of the 25th International Conference on Machine Learning. 41-47. 10.1145/1390156.1390162.”

    -

    Observation Space#

    +

    Observation Space

    The observation is discrete and consists of 4 elements:

    • 0: The x coordinate of the agent

      • @@ -372,7 +377,7 @@

      Observation Space -

      Action Space#

      +

      Action Space

      The action is discrete and consists of 4 elements:

      • 0: Move up

        • @@ -382,7 +387,7 @@

        Action Space -

        Reward Space#

        +

        Reward Space

        The reward is 3-dimensional:

        • 0: -1 if killed by an enemy, else 0

          • @@ -391,15 +396,15 @@

          Reward Space -

          Starting State#

          +

          Starting State

          The agent starts at the home position with no gold or diamond.

    -

    Episode Termination#

    +

    Episode Termination

    The episode terminates when the agent returns home, or when the agent is killed by an enemy.

    -

    Credits#

    +

    Credits

    The home asset is from https://limezu.itch.io/serenevillagerevamped The gold, enemy and gem assets are from https://ninjikin.itch.io/treasure

    @@ -504,8 +509,8 @@

    Credits#< - - + + diff --git a/environments/water-reservoir/index.html b/environments/water-reservoir/index.html index a3b7dbb0..1168e99d 100644 --- a/environments/water-reservoir/index.html +++ b/environments/water-reservoir/index.html @@ -11,7 +11,7 @@ - + Water-Reservoir - MO-Gymnasium Documentation @@ -215,6 +215,7 @@
  • Install
  • API
  • Wrappers
    • +
  • Vector Wrappers
  • MORL Baselines

    • Environments

    @@ -234,11 +235,14 @@
  • MO-Mountaincar
  • MO-Mountaincarcontinuous
  • MO-Lunar-Lander
    • +
  • MO-Lunar-Lander-Continuous
  • Miscellaneous @@ -317,9 +321,10 @@
    -

    Water-Reservoir#

    +

    Water-Reservoir

    -../../_images/water-reservoir.gif +../../_images/water-reservoir.gif +

    • @@ -357,7 +362,7 @@

    Water-Reservoir -

    Description#

    +

    Description

    A Water reservoir environment. The agent executes a continuous action, corresponding to the amount of water released by the dam.

    A. Castelletti, F. Pianosi and M. Restelli, “Tree-based Fitted Q-iteration for Multi-Objective Markov Decision problems,” @@ -365,16 +370,16 @@

    Description -

    Observation Space#

    +

    Observation Space

    The observation is a float corresponding to the current level of the reservoir.

    -

    Action Space#

    +

    Action Space

    The action is a float corresponding to the amount of water released by the dam. If normalized_action is True, the action is a float between 0 and 1 corresponding to the percentage of water released by the dam.

    -

    Reward Space#

    +

    Reward Space

    There are up to 4 rewards:

    • cost due to excess level wrt a flooding threshold (upstream)

      • @@ -385,11 +390,11 @@

      Reward Space -

      Starting State#

      +

      Starting State

      The reservoir is initialized with a random level between 0 and 160.

    -

    Arguments#

    +

    Arguments

    - render_mode: The render mode to use. Can be 'human', 'rgb_array' or 'ansi'.
 - time_limit: The maximum number of steps until the episode is truncated.
 - nO: The number of objectives to use. Can be 2, 3 or 4.
@@ -400,7 +405,7 @@ 
    Arguments
-
    Credits#
    
+
    Credits
    
 
    Code from:
 Mathieu Reymond.
 Ported from:
@@ -508,8 +513,8 @@ 
    Credits#<
     
     
 
-    
-    
+    
+    
     
     
     
diff --git a/examples/citation/index.html b/examples/citation/index.html
index baae2629..89d6c0c3 100644
--- a/examples/citation/index.html
+++ b/examples/citation/index.html
@@ -11,7 +11,7 @@
 
         
 
-    
+    
         Citation - MO-Gymnasium Documentation
       
     
@@ -215,6 +215,7 @@
 
  • Install
    • 
 
  • API
    • 
 
  • Wrappers
    • 
+
  • Vector Wrappers
    • 
 
  • MORL Baselines
    • 
 
 
    Environments
    
@@ -234,11 +235,14 @@
 
  • MO-Mountaincar
    • 
 
  • MO-Mountaincarcontinuous
    • 
 
  • MO-Lunar-Lander
    • 
+
  • MO-Lunar-Lander-Continuous
    • 
 
 
 
  • Miscellaneous
@@ -326,7 +330,7 @@
           
    
             
             
    
-
    Citation#
    
+
    Citation
    
 
    If you use this repository in your research, please cite:
    
 
    @inproceedings{felten_toolkit_2023,
 	author = {Felten, Florian and Alegre, Lucas N. and Now{\'e}, Ann and Bazzan, Ana L. C. and Talbi, El Ghazali and Danoy, Gr{\'e}goire and Silva, Bruno C. {\relax da}},
@@ -412,8 +416,8 @@ 
    Citation
     
     
 
-    
-    
+    
+    
     
     
     
diff --git a/examples/morl_baselines/index.html b/examples/morl_baselines/index.html
index 21c6a276..f52abf03 100644
--- a/examples/morl_baselines/index.html
+++ b/examples/morl_baselines/index.html
@@ -8,10 +8,10 @@
     
     
     
-
+
         
 
-    
+    
         MORL Baselines - MO-Gymnasium Documentation
       
     
@@ -215,6 +215,7 @@
 
  • Install
    • 
 
  • API
    • 
 
  • Wrappers
    • 
+
  • Vector Wrappers
    • 
 
  • MORL Baselines
    • 
 
 
    Environments
    
@@ -234,11 +235,14 @@
 
  • MO-Mountaincar
    • 
 
  • MO-Mountaincarcontinuous
    • 
 
  • MO-Lunar-Lander
    • 
+
  • MO-Lunar-Lander-Continuous
    • 
 
 
    • 
 
  • Miscellaneous
@@ -326,7 +330,7 @@
    • +
    Vector Wrappers
    @@ -416,8 +420,8 @@

    MORL Baselines - + + diff --git a/examples/publications/index.html b/examples/publications/index.html index 679e9a25..04305791 100644 --- a/examples/publications/index.html +++ b/examples/publications/index.html @@ -11,7 +11,7 @@ - + List of Publications - MO-Gymnasium Documentation @@ -215,6 +215,7 @@
  • Install
  • API
  • Wrappers
    • +
  • Vector Wrappers
  • MORL Baselines

    • Environments

    @@ -234,11 +235,14 @@
  • MO-Mountaincar
  • MO-Mountaincarcontinuous
  • MO-Lunar-Lander
    • +
  • MO-Lunar-Lander-Continuous
  • Miscellaneous @@ -326,7 +330,7 @@
    -

    List of Publications#

    +

    List of Publications

    MO-Gymnasium (formerly MO-Gym) was first published in:

    Environments

    @@ -232,11 +233,14 @@
  • MO-Mountaincar
  • MO-Mountaincarcontinuous
  • MO-Lunar-Lander
    • +
  • MO-Lunar-Lander-Continuous
  • Miscellaneous @@ -323,7 +327,7 @@

    Index

    L

    • @@ -333,15 +337,21 @@

    L

    M

    @@ -412,8 +422,8 @@

    M

    - - + + diff --git a/index.html b/index.html index 899ecde3..6b7864c4 100644 --- a/index.html +++ b/index.html @@ -11,7 +11,7 @@ - + MO-Gymnasium Documentation @@ -215,6 +215,7 @@
  • Install
  • API
  • Wrappers
    • +
  • Vector Wrappers
  • MORL Baselines

    • Environments

    @@ -234,11 +235,14 @@
  • MO-Mountaincar
  • MO-Mountaincarcontinuous
  • MO-Lunar-Lander
    • +
  • MO-Lunar-Lander-Continuous
  • Miscellaneous @@ -344,12 +348,13 @@

    -MO-HalfCheetah gif +MO-HalfCheetah gif +

    MO-Gymnasium is an open source Python library for developing and comparing multi-objective reinforcement learning algorithms by providing a standard API to communicate between learning algorithms and environments, as well as a standard set of environments compliant with that API. Essentially, the environments follow the standard Gymnasium API, but return vectorized rewards as numpy arrays.

    The documentation website is at mo-gymnasium.farama.org, and we have a public discord server (which we also use to coordinate development work) that you can join here: https://discord.gg/bnJ6kubTg6.

    -

    API#

    +

    API

    As for Gymnasium, the MO-Gymnasium API models environments as simple Python env classes. Creating environment instances and interacting with them is very simple - here’s an example using the “minecart-v0” environment:

    import gymnasium as gym
 import mo_gymnasium as mo_gym
@@ -363,14 +368,14 @@ 
    API#
    
 next_obs, vector_reward, terminated, truncated, info = env.step(your_agent.act(obs))
 
 # Optionally, you can scalarize the reward function with the LinearReward wrapper
-env = mo_gym.LinearReward(env, weight=np.array([0.8, 0.2, 0.2]))
+env = mo_gym.wrappers.LinearReward(env, weight=np.array([0.8, 0.2, 0.2]))

    For details on multi-objective MDP’s (MOMDP’s) and other MORL definitions, see A practical guide to multi-objective reinforcement learning and planning.

    You can also check more examples in this colab notebook! MO-Gym Demo in Colab

    -

    Install#

    +

    Install

    To install MO-Gymnasium, use:

    pip install mo-gymnasium
    @@ -378,7 +383,7 @@

    Install#<

    This does not include dependencies for all families of environments (some can be problematic to install on certain systems). You can install these dependencies for one family like pip install "mo-gymnasium[mujoco]" or use pip install "mo-gymnasium[all]" to install all dependencies.

    -

    Citing#

    +

    Citing

    If you use this repository in your research, please cite:

    @inproceedings{felten_toolkit_2023,
 	author = {Felten, Florian and Alegre, Lucas N. and Now{\'e}, Ann and Bazzan, Ana L. C. and Talbi, El Ghazali and Danoy, Gr{\'e}goire and Silva, Bruno C. {\relax da}},
@@ -454,8 +459,8 @@ 
    Citing#
-    
+    
+    
     
     
     
diff --git a/introduction/api/index.html b/introduction/api/index.html
index 9f36acf2..91ab4264 100644
--- a/introduction/api/index.html
+++ b/introduction/api/index.html
@@ -11,7 +11,7 @@
 
         
 
-    
+    
         API - MO-Gymnasium Documentation
       
     
@@ -215,6 +215,7 @@
 
  • Install
    • 
 
  • API
    • 
 
  • Wrappers
    • 
+
  • Vector Wrappers
    • 
 
  • MORL Baselines
    • 
 
 
    Environments
    
@@ -234,11 +235,14 @@
 
  • MO-Mountaincar
    • 
 
  • MO-Mountaincarcontinuous
    • 
 
  • MO-Lunar-Lander
    • 
+
  • MO-Lunar-Lander-Continuous
    •
  • Miscellaneous @@ -326,7 +330,7 @@
    -

    API#

    +

    API

    As for Gymnasium, the MO-Gymnasium API models environments as simple Python env classes. Creating environment instances and interacting with them is very simple - here’s an example using the “minecart-v0” environment:

    import gymnasium as gym
 import mo_gymnasium as mo_gym
@@ -340,7 +344,7 @@ 
    API#
    
 next_obs, vector_reward, terminated, truncated, info = env.step(your_agent.act(obs))
 
 # Optionally, you can scalarize the reward function with the LinearReward wrapper
-env = mo_gym.LinearReward(env, weight=np.array([0.8, 0.2, 0.2]))
+env = mo_gym.wrappers.LinearReward(env, weight=np.array([0.8, 0.2, 0.2]))

    For details on multi-objective MDP’s (MOMDP’s) and other MORL definitions, see A practical guide to multi-objective reinforcement learning and planning.

    @@ -421,8 +425,8 @@

    API#

    - - + + diff --git a/introduction/install/index.html b/introduction/install/index.html index 549b43b3..d09f6d3b 100644 --- a/introduction/install/index.html +++ b/introduction/install/index.html @@ -11,7 +11,7 @@ - + Install - MO-Gymnasium Documentation @@ -215,6 +215,7 @@
  • Install
  • API
  • Wrappers
    • +
  • Vector Wrappers
  • MORL Baselines

    • Environments

    @@ -234,11 +235,14 @@
  • MO-Mountaincar
  • MO-Mountaincarcontinuous
  • MO-Lunar-Lander
    • +
  • MO-Lunar-Lander-Continuous
  • Miscellaneous @@ -326,7 +330,7 @@
    -

    Install#

    +

    Install

    To install MO-Gymnasium, use:

    pip install mo-gymnasium
    @@ -408,8 +412,8 @@

    Install#< - - + + diff --git a/objects.inv b/objects.inv index 33c144de..3ba6d078 100644 Binary files a/objects.inv and b/objects.inv differ diff --git a/release_notes/index.html b/release_notes/index.html index baa0c43f..45bf2050 100644 --- a/release_notes/index.html +++ b/release_notes/index.html @@ -11,7 +11,7 @@ - + Release Notes - MO-Gymnasium Documentation @@ -215,6 +215,7 @@
  • Install
  • API
  • Wrappers
    • +
  • Vector Wrappers
  • MORL Baselines

    • Environments

    @@ -234,11 +235,14 @@
  • MO-Mountaincar
  • MO-Mountaincarcontinuous
  • MO-Lunar-Lander
    • +
  • MO-Lunar-Lander-Continuous

  • Miscellaneous @@ -326,9 +330,54 @@
    -

    Release Notes#

    +

    Release Notes

    +
    +

    v1.2.0: MO-Gymnasium 1.2.0 Release: Update Gymnasium to v1.0.0, New Mountaincar Environments, Documentation and Test Improvements, and more

    +

    Released on 2024-10-16 - GitHub - PyPI

    +

    Breaking Changes

    +
      +
    • Similar to Gymnasium v1.0, VecEnvs now differ from normal Envs. The associated wrappers also differ. See Gymnasium 1.0.0 release notes.
      • +
    • Wrappers have been moved to their wrappers subpackage, e.g., from mo_gymnasium import MORecordEpisodeStatistics -> from mo_gymnasium.wrappers import MORecordEpisodeStatistics. Vector wrappers can be found under mo-gymnasium.wrappers.vector. See the tests/ folder or our documentation for example usage.
      • +
    +

    Environments

    + +

    Documentation and Tests

    + +

    Bug Fixes

    + +

    New Contributors

    + +

    Full Changelog: v1.1.0...v1.2.0

    -

    v1.1.0: MO-Gymnasium 1.1.0 Release: New MuJoCo environments, Mirrored Deep Sea Treasure, Fruit Tree rendering, and more#

    +

    v1.1.0: MO-Gymnasium 1.1.0 Release: New MuJoCo environments, Mirrored Deep Sea Treasure, Fruit Tree rendering, and more

    Released on 2024-03-11 - GitHub - PyPI

    Environments

      @@ -352,7 +401,7 @@

      Bug fixes

    Full Changelog: v1.0.1...v1.1.0

    -

    v1.0.1: MO-Gymnasium 1.0.1 Release: Support Gymnasium 0.29, breakable-bottles pygame render, and more#

    +

    v1.0.1: MO-Gymnasium 1.0.1 Release: Support Gymnasium 0.29, breakable-bottles pygame render, and more

    Released on 2023-08-24 - GitHub - PyPI

    Environments

      @@ -379,7 +428,7 @@

      Bug fixes

    Full Changelog: v1.0.0...v1.0.1

    -

    v1.0.0: MO-Gymnasium becomes mature#

    +

    v1.0.0: MO-Gymnasium becomes mature

    Released on 2023-06-12 - GitHub - PyPI

    MO-Gymnasium 1.0.0 Release Notes

    We are thrilled to introduce the mature release of MO-Gymnasium, a standardized API and collection of environments designed for Multi-Objective Reinforcement Learning (MORL).

    @@ -391,7 +440,7 @@

    MO-Gymnasium 1.0.0 Release Notes

    reward = forward_reward - ctrl_cost

    With MORL, users have the flexibility to determine the compromises they desire based on their preferences for each objective. Consequently, the environments in MO-Gymnasium do not have predefined weights. Thus, MO-Gymnasium extends the capabilities of Gymnasium to the multi-objective setting, where the agents receives a vectorial reward.

    For example, here is an illustration of the multiple policies learned by an MORL agent for the mo-halfcheetah domain, balancing between saving battery and speed:

    - +

    This release marks the first mature version of MO-Gymnasium within Farama, indicating that the API is stable, and we have achieved a high level of quality in this library.

    API

    v0.3.4...v1.0.0

    -

    v0.3.4: MO-Gymnasium 0.3.4 Release: Known Pareto Front, improved renders and documentation#

    +

    v0.3.4: MO-Gymnasium 0.3.4 Release: Known Pareto Front, improved renders and documentation

    Released on 2023-03-14 - GitHub - PyPI

    Changelogs

    Environments

    @@ -470,7 +519,7 @@

    New Contributors

    Full Changelog: v0.3.3...0.3.4

    -

    v0.3.3: MO-Gymnasium 0.3.3 Release: Policy Evaluation bug fix, better documentation page#

    +

    v0.3.3: MO-Gymnasium 0.3.3 Release: Policy Evaluation bug fix, better documentation page

    Released on 2023-02-13 - GitHub - PyPI

    New improvements/features

      @@ -489,7 +538,7 @@

      Documentation

    Full Changelog: 0.3.2...v0.3.3

    -

    MO-Gymnasium 0.3.2 Release: Bug fixes, improved webpage#

    +

    MO-Gymnasium 0.3.2 Release: Bug fixes, improved webpage

    Released on 2023-02-03 - GitHub - PyPI

    Bug fixes

      @@ -502,7 +551,7 @@

      Documentation

    Full Changelog: 0.3.1...0.3.2

    -

    MO-Gymnasium 0.3.1 Release: Improved documentation and MuJoco MO-Reacher environment#

    +

    MO-Gymnasium 0.3.1 Release: Improved documentation and MuJoco MO-Reacher environment

    Released on 2023-02-02 - GitHub - PyPI

    This minor release adds "mo-reacher-v4", a MuJoco version of the Reacher environment, fixes a bug in Lunar Lander and improves the library documentation.

    Environments

    @@ -521,7 +570,7 @@

    Bug Fixes

    Full Changelog: 0.3.0...0.3.1

    -

    MO-Gymnasium 0.3.0 Release: Migrate to Gymnasium#

    +

    MO-Gymnasium 0.3.0 Release: Migrate to Gymnasium

    Released on 2023-01-23 - GitHub - PyPI

    This release marks our first release as part of the Farama Foundation. Benefitting the Farama structure, this library should reach a higher level of quality and more integration with the tools from the RL community.

    Breaking changes

    @@ -544,7 +593,7 @@

    Community

    Full Changelog: 0.2.1...0.3.0

    -

    0.2.1#

    +

    0.2.1

    Released on 2022-12-09 - GitHub - PyPI

    • 5 new environments: fishwood-v0 (ESR), mo-MountainCarContinuous-v0, water-reservoir-v0, mo-highway-v0 and mo-highway-fast-v0;
      • @@ -554,15 +603,15 @@

      0.2.1 -

      0.2.0#

      +

      0.2.0

      Released on 2022-09-25 - GitHub - PyPI

      Support for new Gym>=0.26 API

    -

    0.1.2#

    +

    0.1.2

    Released on 2022-09-25 - GitHub - PyPI

    -

    0.1.1#

    +

    0.1.1

    Released on 2022-08-24 - GitHub - PyPI

    @@ -615,6 +664,7 @@

    0.1.1

  • Miscellaneous @@ -389,8 +393,8 @@ - - + + diff --git a/searchindex.js b/searchindex.js index c35fa381..9ee85872 100644 --- a/searchindex.js +++ b/searchindex.js @@ -1 +1 @@ -Search.setIndex({"docnames": ["404", "README", "citing/citing", "community/community", "environments/breakable-bottles", "environments/classical", "environments/deep-sea-treasure", "environments/deep-sea-treasure-concave", "environments/deep-sea-treasure-mirrored", "environments/fishwood", "environments/four-room", "environments/fruit-tree", "environments/grid-world", "environments/minecart", "environments/minecart-deterministic", "environments/minecart-rgb", "environments/misc", "environments/mo-ant", "environments/mo-ant-2d", "environments/mo-halfcheetah", "environments/mo-highway", "environments/mo-highway-fast", "environments/mo-hopper", "environments/mo-hopper-2d", "environments/mo-humanoid", "environments/mo-lunar-lander", "environments/mo-lunar-lander-continuous", "environments/mo-mountaincar", "environments/mo-mountaincarcontinuous", "environments/mo-reacher", "environments/mo-supermario", "environments/mo-swimmer", "environments/mo-walker2d", "environments/mujoco", "environments/resource-gathering", "environments/water-reservoir", "examples/citation", "examples/morl_baselines", "examples/publications", "index", "introduction/api", "introduction/install", "release_notes", "tutorials/custom_env", "wrappers/wrappers"], "filenames": ["404.md", "README.md", "citing/citing.md", "community/community.md", "environments/breakable-bottles.md", "environments/classical.md", "environments/deep-sea-treasure.md", "environments/deep-sea-treasure-concave.md", "environments/deep-sea-treasure-mirrored.md", "environments/fishwood.md", "environments/four-room.md", "environments/fruit-tree.md", "environments/grid-world.md", "environments/minecart.md", "environments/minecart-deterministic.md", "environments/minecart-rgb.md", "environments/misc.md", "environments/mo-ant.md", "environments/mo-ant-2d.md", "environments/mo-halfcheetah.md", "environments/mo-highway.md", "environments/mo-highway-fast.md", "environments/mo-hopper.md", "environments/mo-hopper-2d.md", "environments/mo-humanoid.md", "environments/mo-lunar-lander.md", "environments/mo-lunar-lander-continuous.md", "environments/mo-mountaincar.md", "environments/mo-mountaincarcontinuous.md", "environments/mo-reacher.md", "environments/mo-supermario.md", "environments/mo-swimmer.md", "environments/mo-walker2d.md", "environments/mujoco.md", "environments/resource-gathering.md", "environments/water-reservoir.md", "examples/citation.md", "examples/morl_baselines.md", "examples/publications.md", "index.md", "introduction/api.md", "introduction/install.md", "release_notes.md", "tutorials/custom_env.md", "wrappers/wrappers.md"], "titles": ["404 - Page Not Found", "MO-Gymnasium documentation", "<no title>", "Community", "Breakable-Bottles", "Classic Control", "Deep-Sea-Treasure", "Deep-Sea-Treasure-Concave", "Deep-Sea-Treasure-Mirrored", "Fishwood", "Four-Room", "Fruit-Tree", "Grid-World", "Minecart", "Minecart-Deterministic", "Minecart-Rgb", "Miscellaneous", "MO-Ant", "MO-Ant-2D", "MO-Halfcheetah", "MO-Highway", "MO-Highway-Fast", "MO-Hopper", "MO-Hopper-2D", "MO-Humanoid", "MO-Lunar-Lander", "MO-Lunar-Lander-Continuous", "MO-Mountaincar", "MO-Mountaincarcontinuous", "MO-Reacher", "MO-Supermario", "MO-Swimmer", "MO-Walker2D", "MuJoCo", "Resource-Gathering", "Water-Reservoir", "Citation", "MORL Baselines", "List of Publications", "API", "API", "Install", "Release Notes", "Creating a custom environment", "Wrappers"], "terms": {"thi": [1, 4, 36, 39, 40, 41, 42, 43, 44], "folder": 1, "contain": [1, 4, 10, 11, 12, 13, 14, 15, 27, 28, 29, 37], "For": [1, 29, 39, 40, 42, 44], "more": [1, 13, 14, 15, 17, 18, 19, 20, 22, 23, 24, 25, 26, 27, 28, 30, 31, 32, 39, 40], "inform": [1, 13, 14, 15, 17, 18, 19, 20, 22, 23, 24, 25, 26, 27, 28, 30, 31, 32, 36, 39], "about": 1, "how": [1, 13, 14, 15, 30, 37], "contribut": [1, 3, 4, 42], "go": [1, 9, 11, 22, 23, 27], "our": [1, 42, 43], "md": [1, 42], "instal": 1, "requir": 1, "packag": [1, 42], "your": [1, 36, 39], "fork": 1, "pip": [1, 39, 41], "r": [1, 44], "doc": [1, 42], "txt": 1, "e": [1, 2, 4, 6, 7, 8, 12, 28, 36, 39, 42], "To": [1, 6, 7, 8, 39, 41], "onc": 1, "cd": 1, "make": [1, 4, 6, 7, 8, 9, 10, 11, 13, 14, 15, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 34, 35, 39, 40, 42, 43, 44], "dirhtml": 1, "rebuild": 1, "automat": [1, 42, 43], "everi": [1, 11, 12], "time": [1, 4, 6, 7, 8, 12, 13, 14, 15, 16, 27, 28, 30, 44], "chang": [1, 6, 7, 8, 42], "i": [1, 3, 4, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 34, 35, 37, 39, 40, 42, 43, 44], "made": [1, 42], "sphinx": 1, "autobuild": 1, "b": 1, "_build": 1, "mo": [2, 3, 5, 13, 14, 15, 16, 33, 37, 38, 39, 40, 41, 43, 44], "gymnasium": [2, 5, 13, 14, 15, 16, 17, 18, 19, 22, 23, 24, 25, 26, 27, 31, 32, 37, 38, 39, 40, 41, 43, 44], "formerli": [2, 38], "gym": [2, 30, 38, 39, 40, 42], "appear": 2, "first": [2, 13, 14, 15, 35, 38, 42, 44], "follow": [2, 10, 13, 14, 15, 39, 40, 42, 43], "workshop": [2, 38], "public": [2, 39], "inproceed": [2, 36, 39], "alegr": [2, 12, 36, 38, 39], "2022bnaic": 2, "author": [2, 36, 39], "luca": [2, 36, 39], "n": [2, 36, 39], "florian": [2, 36, 39], "felten": [2, 12, 36, 38, 39], "el": [2, 36, 39], "ghazali": [2, 36, 39], "talbi": [2, 36, 39], "gr": [2, 36, 39], "goir": [2, 36, 39], "danoi": [2, 36, 39], "ann": [2, 36, 39], "now": [2, 36, 39, 42], "ana": [2, 36, 39], "l": [2, 36, 39, 44], "c": [2, 36, 39], "bazzan": [2, 36, 39], "bruno": [2, 36, 39], "relax": [2, 36, 39], "da": [2, 36, 39], "silva": [2, 36, 39], "titl": [2, 36, 39], "A": [2, 4, 10, 16, 17, 18, 21, 27, 28, 35, 36, 38, 39, 40, 44], "librari": [2, 38, 39, 42], "multi": [2, 5, 9, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 30, 31, 32, 33, 35, 36, 38, 39, 40, 42, 43], "object": [2, 5, 9, 12, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 30, 31, 32, 33, 35, 36, 38, 39, 40, 42, 43], "reinforc": [2, 4, 9, 10, 36, 38, 39, 40, 42], "learn": [2, 4, 9, 10, 34, 36, 38, 39, 40, 42], "environ": [2, 4, 5, 6, 7, 8, 9, 10, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 35, 38, 39, 40, 41, 44], "booktitl": [2, 36, 39], "proceed": [2, 34, 36, 39], "34th": 2, "benelux": 2, "confer": [2, 34, 35, 36, 39], "artifici": 2, "intellig": 2, "bnaic": [2, 38], "benelearn": 2, "2022": [2, 5, 12, 38, 42], "year": [2, 36, 39], "If": [3, 13, 14, 15, 17, 18, 22, 23, 35, 36, 39, 43], "you": [3, 36, 39, 40, 41, 42, 43], "want": 3, "help": 3, "u": 3, "out": [3, 35], "reach": [3, 6, 7, 8, 10, 11, 12, 16, 27, 28, 30, 42], "simpli": 3, "ask": 3, "question": 3, "can": [3, 4, 9, 11, 13, 14, 15, 35, 39, 40, 41, 42], "join": [3, 39], "farama": [3, 13, 14, 15, 39, 42], "discord": [3, 39], "server": [3, 39], "here": [3, 10, 39, 40, 42], "asid": 3, "from": [3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 34, 35, 42, 43, 44], "main": [3, 13, 14, 15, 25, 26], "contributor": [3, 42], "some": [3, 39, 41, 43], "peopl": 3, "have": [3, 4, 12, 39, 42], "also": [3, 16, 39, 40, 42], "project": 3, "variou": [3, 37], "wai": [3, 10], "we": [3, 39, 42, 43], "would": 3, "like": [3, 39, 41, 44], "thank": 3, "them": [3, 4, 39, 40], "all": [3, 17, 18, 34, 39, 41, 42, 44], "The": [3, 4, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 34, 35, 39, 42, 43], "minecart": [3, 16, 39, 40, 42], "v0": [3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 20, 21, 27, 28, 29, 30, 33, 34, 35, 39, 40], "env": [3, 5, 12, 13, 14, 15, 16, 17, 18, 19, 20, 22, 23, 24, 25, 26, 27, 31, 32, 33, 39, 40, 42, 43, 44], "refactor": [3, 13, 14, 15], "http": [3, 4, 6, 7, 8, 13, 14, 15, 34, 35, 39], "github": [3, 13, 14, 15, 42], "com": [3, 13, 14, 15], "axelabel": 3, "dynmorl": 3, "deep": [3, 12], "sea": [3, 12], "treasur": [3, 4, 12, 34], "fruit": [3, 12], "tree": [3, 12, 35], "supermario": [3, 16], "ar": [3, 4, 13, 14, 15, 16, 34, 35, 42, 43, 44], "base": [3, 4, 13, 14, 15, 29, 33, 35, 38, 42], "runzheyang": 3, "morl": [3, 6, 7, 8, 9, 39, 40, 42], "four": [3, 12, 29], "room": [3, 12], "mike": [3, 10], "gimelfarb": [3, 10], "successor": [3, 10], "featur": [3, 10, 42], "transfer": [3, 10], "fishwood": [3, 12, 42], "code": [3, 6, 7, 8, 9, 10, 13, 14, 15, 35, 42], "wa": [3, 4, 6, 7, 8, 13, 14, 15, 38, 42], "provid": [3, 9, 39, 42], "deni": [3, 9], "steckelmach": [3, 9], "conor": 3, "f": [3, 35], "hay": 3, "water": [3, 11, 12, 16, 42], "reservoir": [3, 16, 42], "mathieu": [3, 35], "reymond": [3, 35], "discret": [4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 20, 21, 25, 27, 29, 30, 33, 34, 42], "3": [4, 6, 7, 8, 10, 13, 14, 15, 17, 18, 20, 21, 22, 23, 25, 26, 27, 29, 30, 34, 35], "dict": 4, "bottles_carri": 4, "bottles_deliv": [4, 12], "2": [4, 6, 7, 8, 9, 11, 13, 14, 15, 17, 18, 19, 20, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 34, 35, 39, 40], "bottles_drop": 4, "multibinari": 4, "locat": [4, 12, 29], "5": [4, 11, 12, 13, 14, 15, 20, 21, 25, 26, 30, 34, 42], "shape": [4, 6, 7, 8, 9, 10, 11, 13, 14, 15, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 34, 35, 43, 44], "high": [4, 6, 7, 8, 9, 10, 11, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 34, 35, 42], "0": [4, 6, 7, 8, 9, 10, 11, 13, 14, 15, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 34, 35, 39, 40, 44], "50": [4, 42], "low": [4, 6, 7, 8, 9, 10, 11, 13, 14, 15, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 34, 35], "inf": [4, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 29, 30, 31, 32, 35], "1": [4, 6, 7, 8, 9, 10, 11, 13, 14, 15, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 34, 35, 44], "import": [4, 6, 7, 8, 9, 10, 11, 13, 14, 15, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 34, 35, 39, 40, 42, 43], "mo_gymnasium": [4, 6, 7, 8, 9, 10, 11, 13, 14, 15, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 34, 35, 39, 40, 42, 43, 44], "implement": [4, 37, 43], "problem": [4, 6, 7, 8, 9, 35, 42], "unbreakablebottl": 4, "breakablebottl": 4, "defin": [4, 5, 16, 29, 43], "section": 4, "4": [4, 6, 7, 8, 10, 13, 14, 15, 24, 25, 26, 29, 30, 34, 35], "paper": 4, "potenti": [4, 12, 42], "multiobject": 4, "approach": 4, "impact": 4, "agent": [4, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 34, 35, 42], "ai": 4, "safeti": 4, "move": [4, 30, 31, 34, 42], "left": [4, 6, 7, 8, 10, 11, 13, 14, 15, 34], "right": [4, 6, 7, 8, 10, 11, 13, 14, 15, 20, 34], "pick": 4, "up": [4, 6, 7, 8, 10, 34, 35], "dictionari": [4, 12], "kei": 4, "current": [4, 6, 7, 8, 35], "number": [4, 35], "carri": 4, "ha": [4, 30, 42], "deliv": [4, 12], "each": [4, 6, 7, 8, 11, 13, 14, 15, 27, 28, 29, 42], "boolean": [4, 44], "flag": [4, 17, 18, 22, 23, 30, 34, 43], "indic": [4, 10, 34, 42], "dimens": [4, 42], "penalti": [4, 5, 6, 7, 8, 12, 27, 28, 30], "step": [4, 6, 7, 8, 9, 27, 28, 30, 35, 38, 39, 40, 42, 43], "bottle_reward": 4, "while": [4, 10, 12, 16], "multipl": [4, 34, 37, 38, 42, 43, 44], "small": [4, 42], "probabl": [4, 9], "drop": [4, 42], "appli": [4, 29, 44], "ground": 4, "when": [4, 6, 7, 8, 9, 10, 11, 13, 14, 15, 30, 34, 42, 43], "size": [4, 11, 43], "prob_drop": 4, "time_penalti": [4, 5, 12], "unbreakable_bottl": 4, "true": [4, 6, 7, 8, 13, 14, 15, 35, 44], "which": [4, 6, 7, 8, 9, 10, 39, 42, 43, 44], "again": 4, "so": 4, "outcom": 4, "revers": [4, 5, 27], "otherwis": [4, 9, 30], "cannot": 4, "origin": [4, 39, 40, 42], "robert": 4, "klassert": 4, "home": [4, 34], "asset": [4, 34, 42], "limezu": [4, 34], "itch": [4, 6, 7, 8, 34], "io": [4, 6, 7, 8, 34], "serenevillagerevamp": [4, 34], "gold": [4, 12, 34], "enemi": [4, 12, 16, 30, 34], "gem": [4, 12, 34], "ninjikin": [4, 34], "pixel": [4, 6, 7, 8, 42], "art": [4, 6, 7, 8, 42], "creat": [4, 6, 7, 8, 39, 40, 42], "assist": [4, 6, 7, 8], "dall": [4, 6, 7, 8], "version": [5, 10, 12, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 42], "": [5, 6, 7, 8, 10, 13, 14, 15, 16, 17, 18, 19, 22, 23, 24, 25, 26, 27, 31, 32, 39, 40, 44], "ob": [5, 12, 16, 33, 39, 40, 42], "action": [5, 12, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 30, 31, 32, 33, 42, 43], "space": [5, 12, 16, 21, 33, 42, 43], "descript": [5, 12, 16, 33], "mountaincar": [5, 28], "continu": [5, 6, 7, 8, 16, 28, 33, 35, 42], "reverse_penalti": 5, "forward_penalti": 5, "mountain": [5, 27, 28, 42], "car": [5, 42], "extra": 5, "forward": [5, 19, 22, 23, 24, 27, 31, 32], "vamplew": [5, 12], "et": [5, 6, 7, 8, 10, 11, 12, 13, 14, 15, 16, 33, 38], "al": [5, 6, 7, 8, 10, 11, 12, 13, 14, 15, 16, 33, 38], "2011": 5, "mountaincarcontinu": [5, 42], "fuel_consumption_penalti": 5, "fuel": [5, 13, 14, 15, 16, 25, 26, 28], "consumpt": [5, 13, 14, 15, 16], "lunar": [5, 42], "lander": [5, 42], "v2": [5, 25, 26, 42], "land": [5, 25, 26], "shaped_reward": 5, "main_engine_fuel": 5, "side_engine_fuel": 5, "lunarland": [5, 25, 26], "similarli": [5, 16], "hung": 5, "11": [6, 7, 22, 23, 42], "23": [6, 42], "7": [6, 11, 12, 13, 14, 15, 42], "classic": [6, 7, 8, 43], "control": [6, 7, 8, 9, 17, 18, 19, 22, 23, 24, 31, 32], "submarin": [6, 7, 8, 12], "2d": [6, 7, 8, 10, 13, 14, 15, 28, 42, 44], "grid": [6, 7, 8], "world": [6, 7, 8], "box": [6, 7, 8, 17, 18, 19, 22, 23, 24, 26, 28, 31, 32, 35], "valu": [6, 7, 8, 11, 12, 38], "10": [6, 7, 8, 11, 12, 34, 35], "x": [6, 7, 8, 17, 18, 22, 23, 24, 30, 31, 32, 34], "y": [6, 7, 8, 17, 18, 34], "coordin": [6, 7, 8, 34, 39], "where": [6, 7, 8, 9, 11, 27, 28, 42], "down": [6, 7, 8, 10, 34], "dimension": [6, 7, 8, 9, 10, 11, 13, 14, 15, 17, 18, 19, 20, 22, 23, 24, 25, 26, 29, 30, 31, 32, 34], "posit": [6, 7, 8, 10, 13, 14, 15, 29, 30, 34], "alwai": [6, 7, 8], "same": [6, 7, 8], "dst_map": [6, 7, 8], "map": [6, 7, 8, 10, 12, 13, 14, 15], "default": [6, 7, 8, 13, 14, 15, 35], "convex": [6, 7, 8], "yang": [6, 7, 8, 11, 12, 16], "2019": [6, 7, 8, 11, 12, 13, 14, 15, 16], "us": [6, 7, 8, 13, 14, 15, 35, 36, 37, 38, 39, 40, 41, 42, 43], "deepseatreasur": [6, 7, 8], "concave_map": [6, 7, 8], "mirrored_map": [6, 7, 8], "float_stat": [6, 7, 8], "adapt": [6, 7, 8, 10], "sourc": [6, 7, 8, 10, 12, 13, 14, 15, 28, 39], "background": [6, 7, 8, 35], "ansimuz": [6, 7, 8], "underwat": [6, 7, 8], "fantasi": [6, 7, 8], "124": [7, 8], "20": [8, 42], "simpl": [9, 39, 40], "fisherman": 9, "either": 9, "fish": [9, 12], "collect": [9, 10, 11, 12, 13, 14, 15, 16, 30, 34, 42], "wood": [9, 12], "expect": 9, "util": [9, 42], "return": [9, 13, 14, 15, 34, 39, 42, 43, 44], "two": [9, 13, 14, 15, 16, 29, 30, 35], "woodproba": 9, "fishproba": 9, "episod": [9, 35, 44], "end": [9, 13, 14, 15], "after": [9, 42, 44], "max_t": 9, "200": 9, "catch": 9, "14": [10, 25, 26, 42], "13": [10, 42], "gridworld": [10, 12], "introduc": [10, 42], "an": [10, 30, 34, 35, 39, 40, 42, 43, 44], "avoid": [10, 16], "those": 10, "neg": [10, 28, 29], "travel": 10, "fix": 10, "goal": [10, 12, 27, 28], "split": 10, "separ": 10, "wall": 10, "passag": 10, "barreto": 10, "andr\u00e9": 10, "nip": 10, "2017": 10, "plu": 10, "binari": [10, 11, 12], "vector": [10, 11, 13, 14, 15, 27, 28, 30, 39, 42, 43, 44], "item": [10, 12], "were": 10, "compon": [10, 42, 44], "blue": 10, "squar": 10, "els": [10, 30, 34], "green": 10, "triangl": 10, "red": 10, "circl": 10, "lower": 10, "g": [10, 12, 42], "maze": 10, "arrai": [10, 39, 40, 42, 43, 44], "see": [10, 13, 14, 15, 17, 18, 19, 20, 22, 23, 24, 25, 26, 27, 28, 30, 31, 32, 39, 40, 42, 43], "exampl": [10, 37, 39, 40, 42], "63": 11, "6": [11, 12, 13, 14, 15, 19, 27, 28, 29, 32], "full": [11, 12, 42], "depth": [11, 12], "d": [11, 12, 38], "leaf": [11, 12], "nutrient": [11, 12], "protein": [11, 12], "carb": [11, 12], "fat": [11, 12], "vitamin": [11, 12], "miner": [11, 12], "chose": 11, "node": 11, "therefor": 11, "receiv": [11, 42], "root": [11, 42], "observ": [12, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 30, 31, 32, 42, 43], "must": [12, 13, 14, 15, 16, 43], "take": 12, "account": 12, "taken": 12, "concav": [12, 42], "2010": 12, "mirror": 12, "harder": 12, "dst": [12, 42], "resourc": [12, 42], "gather": [12, 42], "chanc": 12, "kill": [12, 30, 34], "barret": 12, "narayanan": [12, 34], "2008": [12, 34], "fish_amount": 12, "wood_amount": 12, "esr": [12, 42], "light": 12, "fire": 12, "eat": 12, "roijer": 12, "2018": 12, "breakabl": 12, "bottl": 12, "cell": 12, "destin": 12, "2021": 12, "nutri1": 12, "nutri6": 12, "item1": 12, "item2": 12, "item3": 12, "three": 12, "differ": 12, "type": [12, 13, 14, 15, 16, 42], "ores": [13, 14, 15, 16], "minim": [13, 14, 15, 16], "abel": [13, 14, 15, 16], "cart": [13, 14, 15], "speed": [13, 14, 15, 16, 20, 42], "sin": [13, 14, 15, 29], "co": [13, 14, 15, 29], "orient": [13, 14, 15], "porcentag": [13, 14, 15], "capac": [13, 14, 15], "fill": [13, 14, 15], "image_observ": [13, 14, 15], "3d": [13, 14, 15, 27], "imag": [13, 14, 15, 16, 35], "mine": [13, 14, 15], "acceler": [13, 14, 15], "brake": [13, 14, 15], "none": [13, 14, 15, 35, 42, 44], "quantiti": [13, 14, 15], "minerium": [13, 14, 15], "retriev": [13, 14, 15], "spars": [13, 14, 15], "second": [13, 14, 15], "consum": [13, 14, 15], "dens": [13, 14, 15], "upper": [13, 14, 15], "corner": [13, 14, 15], "render_mod": [13, 14, 15, 35], "render": [13, 14, 15, 35, 43], "mode": [13, 14, 15, 35], "rgb_arrai": [13, 14, 15, 35], "human": [13, 14, 15, 35], "rgb": [13, 14], "frame_skip": [13, 14, 15], "mani": [13, 14, 15], "repeat": [13, 14, 15], "incremental_frame_skip": [13, 14, 15], "whether": [13, 14, 15, 35], "increment": [13, 14, 15], "config": [13, 14, 15], "path": [13, 14, 15], "json": [13, 14, 15], "configur": [13, 14, 15], "file": [13, 14, 15, 42, 43], "foundat": [13, 14, 15, 42], "blob": [13, 14, 15], "mine_config": [13, 14, 15], "axel": [13, 14, 15], "480": 15, "255": [15, 30], "includ": [16, 39, 41], "other": [16, 17, 18, 22, 23, 39, 40, 42, 44], "cost_flood": 16, "deficit_wat": 16, "execut": [16, 35], "correspond": [16, 35], "amount": [16, 35], "releas": [16, 35], "dam": [16, 35], "pianosi": [16, 35], "2013": 16, "ore1": 16, "ore2": 16, "highwai": [16, 42], "fast": [16, 42], "right_lan": 16, "collis": [16, 20], "neighbour": 16, "vehicl": 16, "stai": 16, "rightest": 16, "lane": [16, 20], "x_po": 16, "death": 16, "coin": [16, 30], "warn": [16, 42], "supermariobrosenv": 16, "support": 16, "limit": 16, "8": [17, 18, 25, 26, 31, 35, 39, 40, 42], "float32": [17, 18, 19, 22, 23, 24, 26, 28, 31, 32, 35], "27": [17, 18, 42], "v4": [17, 18, 19, 22, 23, 24, 29, 31, 32, 33, 42], "antenv": [17, 18], "veloc": [17, 18, 24, 29, 31, 32, 33], "cost": [17, 18, 19, 22, 23, 24, 25, 26, 31, 32, 35], "cost_object": [17, 18, 22, 23], "set": [17, 18, 22, 23, 39, 42, 43], "fals": [17, 18, 22, 23], "ad": [17, 18, 22, 23, 43], "healthi": [17, 18], "17": [19, 24, 32], "halfcheetahenv": 19, "run": [19, 24, 32, 43, 44], "highwayenv": 20, "reward": [21, 39, 40, 42, 43, 44], "highwayfastenv": 21, "hopperenv": [22, 23], "axi": [22, 23], "jump": [22, 23], "z": [22, 23], "376": 24, "humanoidenv": 24, "100": [25, 26, 30, 44], "crash": [25, 26], "successfulli": [25, 26], "engin": [25, 26], "side": [25, 26], "07": [27, 28], "top": [27, 28], "norm": 28, "9": 29, "mujoco": [29, 39, 41], "angl": 29, "central": 29, "elbow": 29, "joint": [29, 35], "angular": 29, "possibl": 29, "zero": [29, 42], "torqu": 29, "distanc": [29, 43], "tip": 29, "arm": 29, "target": 29, "comput": [29, 42, 43], "r_i": 29, "finger_tip_coord": 29, "target_i": 29, "256": 30, "240": 30, "25": [30, 42], "supermariobro": 30, "super": 30, "mario": [30, 42], "bro": 30, "far": 30, "much": 30, "pass": [30, 42], "between": [30, 35, 39, 42, 44], "di": 30, "point": 30, "swimmerenv": 31, "walker2denv": 32, "reacher": 33, "target_1": 33, "target_2": 33, "target_3": 33, "target_4": 33, "hopper": [33, 42], "height": 33, "energi": 33, "halfcheetah": [33, 42], "similar": 33, "xu": 33, "2020": 33, "walker2d": 33, "ant": 33, "x_veloc": [33, 42], "y_veloc": 33, "swimmer": 33, "humanoid": 33, "humonoid": 33, "barrett": 34, "leon": 34, "srini": 34, "optim": [34, 38, 42], "polici": [34, 38], "criteria": 34, "25th": 34, "intern": [34, 35], "machin": 34, "41": [34, 42], "47": [34, 42], "1145": 34, "1390156": 34, "1390162": 34, "consist": 34, "element": [34, 42], "diamond": 34, "castelletti": 35, "m": 35, "restelli": 35, "fit": 35, "q": 35, "iter": [35, 44], "markov": 35, "decis": 35, "2012": 35, "neural": [35, 36, 39], "network": 35, "ijcnn": 35, "brisban": 35, "qld": 35, "australia": 35, "pp": 35, "doi": 35, "1109": 35, "6252759": 35, "float": [35, 43, 44], "level": [35, 42], "normalized_act": 35, "percentag": 35, "There": 35, "due": 35, "excess": 35, "wrt": 35, "flood": 35, "threshold": 35, "upstream": 35, "deficit": 35, "suppli": 35, "demand": 35, "hydroelectr": 35, "downstream": 35, "By": 35, "onli": 35, "initi": [35, 43], "random": 35, "160": 35, "ansi": 35, "time_limit": 35, "maximum": 35, "until": 35, "truncat": [35, 39, 40, 42, 43], "nO": 35, "penal": 35, "select": 35, "bound": [35, 42], "normal": [35, 42, 44], "initial_st": 35, "port": 35, "simon": 35, "parisi": 35, "sky": 35, "paulina": 35, "riva": 35, "opengameart": 35, "org": [35, 39], "content": 35, "repositori": [36, 37, 39, 43], "research": [36, 38, 39], "pleas": [36, 38, 39], "cite": 36, "felten_toolkit_2023": [36, 39], "toolkit": [36, 38, 39], "reliabl": [36, 38, 39], "benchmark": [36, 38, 39], "37th": [36, 39], "process": [36, 39], "system": [36, 39, 41], "neurip": [36, 38, 39], "2023": [36, 38, 39, 42], "algorithm": [37, 39], "under": [37, 42], "api": [37, 42, 43], "It": [37, 39, 40, 42, 43], "wrapper": [37, 39, 40, 42], "publish": 38, "submiss": 38, "open": [38, 39], "pull": [38, 43], "request": 38, "add": [38, 42], "miss": [38, 42], "entri": 38, "sampl": 38, "effici": 38, "via": 38, "gener": [38, 42, 43], "improv": 38, "priorit": 38, "aama": 38, "hyperparamet": 38, "modem": 38, "leverag": 38, "approxim": 38, "model": [38, 39, 40], "distribut": 38, "pareto": [38, 43], "cai": 38, "welfar": 38, "fair": 38, "fan": 38, "person": 38, "budget": 38, "ivanov": 38, "2024": [38, 42], "decomposit": 38, "taxonomi": 38, "framework": 38, "guarante": 38, "align": 38, "rodriguez": 38, "soto": 38, "mofl": 38, "feder": 38, "hartmann": 38, "standard": [39, 42], "suit": 39, "python": [39, 40, 42], "develop": 39, "compar": 39, "commun": [39, 42], "well": [39, 42, 43], "compliant": 39, "essenti": [39, 43], "numpi": [39, 40, 42, 43, 44], "document": [39, 43], "websit": [39, 42], "work": 39, "gg": 39, "bnj6kubtg6": 39, "As": [39, 40], "class": [39, 40, 44], "instanc": [39, 40, 42], "interact": [39, 40], "veri": [39, 40, 43], "mo_gym": [39, 40, 42], "np": [39, 40, 42], "info": [39, 40, 42, 43, 44], "reset": [39, 40, 42, 43], "vector_reward": [39, 40, 42], "next_ob": [39, 40, 42], "termin": [39, 40, 42, 43], "your_ag": [39, 40, 42], "act": [39, 40, 42], "option": [39, 40, 42, 43], "scalar": [39, 40, 42, 44], "function": [39, 40, 42], "linearreward": [39, 40, 42], "weight": [39, 40, 42, 44], "detail": [39, 40], "mdp": [39, 40, 42], "momdp": [39, 40, 42], "definit": [39, 40], "practic": [39, 40], "guid": [39, 40], "plan": [39, 40], "check": [39, 40], "colab": [39, 40], "notebook": [39, 40], "doe": [39, 41, 44], "depend": [39, 41], "famili": [39, 41], "problemat": [39, 41], "certain": [39, 41], "one": [39, 41], "03": 42, "pypi": 42, "lucasalegr": 42, "87": 42, "ffelten": 42, "79": 42, "unwrap": 42, "access": 42, "reward_spac": [42, 43], "77": 42, "fruit_tre": 42, "tomekst": 42, "81": 42, "group": 42, "83": 42, "80": 42, "updat": 42, "citat": 42, "86": 42, "unpin": 42, "kallinteri": 42, "andrea": 42, "84": 42, "changelog": 42, "08": [42, 44], "24": 42, "75": 42, "momaxandskipobserv": 42, "76": 42, "modifi": 42, "part": [42, 43], "info_dict": 42, "ianleongudri": 42, "69": 42, "order": 42, "wrap": [42, 44], "morecordepisodestatist": 42, "70": 42, "73": 42, "tuto": 42, "custom": 42, "creation": 42, "72": 42, "test": 42, "worker": 42, "67": 42, "pf": 42, "cc": 42, "determinist": 42, "74": 42, "06": 42, "12": 42, "thrill": 42, "design": 42, "expand": 42, "capabl": 42, "rl": 42, "scenario": 42, "need": 42, "mai": 42, "conflict": 42, "repres": 42, "distinct": 42, "In": 42, "context": 42, "trade": 42, "off": 42, "combin": 42, "linearli": 42, "predefin": 42, "shown": 42, "snippet": 42, "ctrl_cost": 42, "self": [42, 43], "control_cost": 42, "forward_reward": 42, "_forward_reward_weight": 42, "With": 42, "user": 42, "flexibl": 42, "determin": 42, "compromis": 42, "thei": [42, 44], "desir": 42, "prefer": 42, "consequ": 42, "do": 42, "thu": 42, "extend": 42, "vectori": 42, "illustr": 42, "domain": 42, "balanc": 42, "save": 42, "batteri": 42, "mark": 42, "within": [42, 43], "stabl": 42, "achiev": 42, "qualiti": 42, "allow": 42, "fall": 42, "back": 42, "singl": 42, "rang": 42, "literatur": 42, "inher": 42, "exhaust": 42, "list": 42, "avail": [42, 44], "addition": 42, "tailor": 42, "monormalizereward": 42, "linearwrapp": 42, "transform": 42, "bump": 42, "51": 42, "52": 42, "accept": 42, "55": 42, "pre": 42, "commit": 42, "spell": 42, "mistak": 42, "56": 42, "method": [42, 43], "57": 42, "59": 42, "60": 42, "61": 42, "65": 42, "caus": 42, "randint": 42, "deprec": 42, "53": 42, "edit": 42, "button": 42, "58": 42, "62": 42, "logo": 42, "64": 42, "pareto_front": [42, 43], "get": 42, "45": 42, "43": 42, "baselin": 42, "readm": 42, "40": 42, "link": 42, "mgoulao": 42, "42": 42, "enabl": 42, "46": 42, "02": 42, "ezpickl": 42, "34": 42, "37": 42, "convers": 42, "33": 42, "eval_mo": 42, "observationspac": 42, "dtype": 42, "35": 42, "gif": 42, "minor": 42, "directli": [42, 44], "26": 42, "pydoc": 42, "31": 42, "hotfix": 42, "vecenv": 42, "30": 42, "01": 42, "benefit": 42, "structur": 42, "should": [42, 43], "higher": 42, "integr": 42, "tool": 42, "break": 42, "been": 42, "renam": 42, "previous": 42, "call": 42, "reli": 42, "instead": 42, "16": 42, "deep_sea_treasur": 42, "gt": 42, "18": 42, "life": 42, "ci": 42, "setup": 42, "19": 42, "init": 42, "Of": 42, "conduct": 42, "21": 42, "09": 42, "revamp": 42, "lint": 42, "bib": 42, "few": [42, 44], "bugfix": 42, "tutori": 43, "goe": 43, "through": 43, "sinc": [43, 44], "close": 43, "ti": 43, "refer": 43, "its": 43, "inherit": 43, "__init__": 43, "constructor": 43, "action_spac": 43, "observation_spac": 43, "attribut": 43, "moreov": 43, "deal": 43, "reward_dim": 43, "integ": 43, "seed": 43, "kwarg": 43, "perform": 43, "next": 43, "gamma": [43, 44], "discount": [43, 44], "front": 43, "known": 43, "oject": 43, "metric": 43, "invert": 43, "igd": 43, "registri": 43, "done": 43, "line": 43, "py": 43, "directori": 43, "registr": 43, "id": 43, "my_env_v0": 43, "entry_point": 43, "my_env_dir": 43, "my_env_fil": 43, "myenv": 43, "pytest": 43, "inspir": 44, "modul": 44, "ndarrai": 44, "dot": 44, "product": 44, "idx": 44, "int": 44, "99": 44, "epsilon": 44, "1e": 44, "index": 44, "touch": 44, "min_r": 44, "max_r": 44, "clip": 44, "min": 44, "max": 44, "env_fn": 44, "callabl": 44, "copi": 44, "bool": 44, "serial": 44, "deque_s": 44, "keep": 44, "track": 44, "cumul": 44, "length": 44, "complet": 44, "look": 44, "dr": 44, "contrari": 44, "t": 44, "elaps": 44, "begin": 44, "output": 44, "form": 44, "care": 44, "befor": 44, "morewordstatist": 44, "final_observ": 44, "num": 44, "_final_observ": 44, "final_info": 44, "_final_info": 44, "num_env": 44, "dim_reward": 44, "_episod": 44}, "objects": {"mo_gymnasium": [[44, 0, 1, "", "LinearReward"], [44, 0, 1, "", "MOClipReward"], [44, 0, 1, "", "MONormalizeReward"], [44, 0, 1, "", "MORecordEpisodeStatistics"], [44, 0, 1, "", "MOSyncVectorEnv"]]}, "objtypes": {"0": "py:class"}, "objnames": {"0": ["py", "class", "Python class"]}, "titleterms": {"404": 0, "page": [0, 42], "Not": 0, "found": 0, "The": 0, "request": 0, "could": 0, "mo": [1, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 42], "gymnasium": [1, 42], "document": [1, 42], "build": 1, "commun": 3, "acknowledg": 3, "breakabl": [4, 42], "bottl": [4, 42], "descript": [4, 6, 7, 8, 9, 10, 11, 13, 14, 15, 17, 18, 19, 20, 22, 23, 24, 25, 26, 29, 30, 31, 32, 34, 35], "action": [4, 6, 7, 8, 9, 10, 11, 13, 14, 15, 29, 34, 35], "space": [4, 6, 7, 8, 9, 10, 11, 13, 14, 15, 17, 18, 19, 20, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 34, 35], "observ": [4, 6, 7, 8, 9, 10, 11, 13, 14, 15, 29, 34, 35], "reward": [4, 6, 7, 8, 9, 10, 11, 13, 14, 15, 17, 18, 19, 20, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 34, 35], "start": [4, 6, 7, 8, 9, 10, 11, 13, 14, 15, 34, 35], "state": [4, 6, 7, 8, 9, 10, 11, 13, 14, 15, 34, 35], "episod": [4, 6, 7, 8, 10, 11, 13, 14, 15, 30, 34], "termin": [4, 6, 7, 8, 9, 10, 11, 13, 14, 15, 30, 34], "argument": [4, 6, 7, 8, 9, 10, 13, 14, 15, 35], "credit": [4, 6, 7, 8, 9, 10, 13, 14, 15, 34, 35], "classic": 5, "control": 5, "deep": [6, 7, 8, 42], "sea": [6, 7, 8, 42], "treasur": [6, 7, 8, 42], "concav": 7, "mirror": [8, 42], "fishwood": 9, "four": 10, "room": 10, "refer": 10, "fruit": [11, 42], "tree": [11, 42], "grid": 12, "world": 12, "minecart": [13, 14, 15], "determinist": 14, "rgb": 15, "miscellan": 16, "ant": [17, 18], "2d": [18, 23], "halfcheetah": 19, "highwai": [20, 21], "fast": 21, "hopper": [22, 23], "humanoid": 24, "lunar": [25, 26], "lander": [25, 26], "continu": 26, "mountaincar": 27, "mountaincarcontinu": 28, "reacher": [29, 42], "supermario": 30, "swimmer": 31, "walker2d": 32, "mujoco": [33, 42], "resourc": 34, "gather": 34, "water": 35, "reservoir": 35, "citat": 36, "morl": 37, "baselin": 37, "list": 38, "public": 38, "api": [39, 40], "instal": [39, 41], "cite": 39, "releas": 42, "note": 42, "v1": 42, "1": [42, 43], "0": 42, "new": [42, 43], "environ": [42, 43], "render": 42, "more": 42, "support": 42, "29": 42, "pygam": 42, "becom": 42, "matur": 42, "v0": 42, "3": [42, 43], "4": [42, 43], "known": 42, "pareto": 42, "front": 42, "improv": 42, "polici": 42, "evalu": 42, "bug": 42, "fix": 42, "better": 42, "2": [42, 43], "webpag": 42, "migrat": 42, "creat": 43, "custom": 43, "class": 43, "regist": 43, "test": 43, "instanti": 43, "your": 43, "wrapper": 44, "linearreward": 44, "monormalizereward": 44, "moclipreward": 44, "mosyncvectorenv": 44, "morecordepisodestatist": 44}, "envversion": {"sphinx.domains.c": 3, "sphinx.domains.changeset": 1, "sphinx.domains.citation": 1, "sphinx.domains.cpp": 9, "sphinx.domains.index": 1, "sphinx.domains.javascript": 3, "sphinx.domains.math": 2, "sphinx.domains.python": 4, "sphinx.domains.rst": 2, "sphinx.domains.std": 2, "sphinx": 60}, "alltitles": {"404 - Page Not Found": [[0, "page-not-found"]], "The requested page could not be found.": [[0, "the-requested-page-could-not-be-found"]], "MO-Gymnasium documentation": [[1, "mo-gymnasium-documentation"]], "Build the Documentation": [[1, "build-the-documentation"]], "Community": [[3, "community"]], "Acknowledgements": [[3, "acknowledgements"]], "Breakable-Bottles": [[4, "breakable-bottles"]], "Description": [[4, "description"], [6, "description"], [7, "description"], [8, "description"], [9, "description"], [10, "description"], [11, "description"], [13, "description"], [14, "description"], [15, "description"], [17, "description"], [18, "description"], [19, "description"], [20, "description"], [22, "description"], [23, "description"], [24, "description"], [25, "description"], [26, "description"], [29, "description"], [30, "description"], [31, "description"], [32, "description"], [34, "description"], [35, "description"]], "Action Space": [[4, "action-space"], [6, "action-space"], [7, "action-space"], [8, "action-space"], [9, "action-space"], [10, "action-space"], [11, "action-space"], [13, "action-space"], [14, "action-space"], [15, "action-space"], [29, "action-space"], [34, "action-space"], [35, "action-space"]], "Observation Space": [[4, "observation-space"], [6, "observation-space"], [7, "observation-space"], [8, "observation-space"], [9, "observation-space"], [10, "observation-space"], [11, "observation-space"], [13, "observation-space"], [14, "observation-space"], [15, "observation-space"], [29, "observation-space"], [34, "observation-space"], [35, "observation-space"]], "Reward Space": [[4, "reward-space"], [6, "reward-space"], [7, "reward-space"], [8, "reward-space"], [9, "reward-space"], [10, "reward-space"], [11, "reward-space"], [13, "reward-space"], [14, "reward-space"], [15, "reward-space"], [17, "reward-space"], [18, "reward-space"], [19, "reward-space"], [20, "reward-space"], [22, "reward-space"], [23, "reward-space"], [24, "reward-space"], [25, "reward-space"], [26, "reward-space"], [29, "reward-space"], [30, "reward-space"], [31, "reward-space"], [32, "reward-space"], [34, "reward-space"], [35, "reward-space"]], "Starting State": [[4, "starting-state"], [6, "starting-state"], [7, "starting-state"], [8, "starting-state"], [9, "starting-state"], [10, "starting-state"], [11, "starting-state"], [13, "starting-state"], [14, "starting-state"], [15, "starting-state"], [34, "starting-state"], [35, "starting-state"]], "Episode Termination": [[4, "episode-termination"], [6, "episode-termination"], [7, "episode-termination"], [8, "episode-termination"], [10, "episode-termination"], [11, "episode-termination"], [13, "episode-termination"], [14, "episode-termination"], [15, "episode-termination"], [30, "episode-termination"], [34, "episode-termination"]], "Arguments": [[4, "arguments"], [6, "arguments"], [7, "arguments"], [8, "arguments"], [9, "arguments"], [10, "arguments"], [13, "arguments"], [14, "arguments"], [15, "arguments"], [35, "arguments"]], "Credits": [[4, "credits"], [6, "credits"], [7, "credits"], [8, "credits"], [9, "credits"], [10, "credits"], [13, "credits"], [14, "credits"], [15, "credits"], [34, "credits"], [35, "credits"]], "Classic Control": [[5, "classic-control"]], "Deep-Sea-Treasure": [[6, "deep-sea-treasure"]], "Deep-Sea-Treasure-Concave": [[7, "deep-sea-treasure-concave"]], "Deep-Sea-Treasure-Mirrored": [[8, "deep-sea-treasure-mirrored"]], "Fishwood": [[9, "fishwood"]], "Termination": [[9, "termination"]], "Four-Room": [[10, "four-room"]], "References": [[10, "references"]], "Fruit-Tree": [[11, "fruit-tree"]], "Grid-World": [[12, "grid-world"]], "Minecart": [[13, "minecart"]], "Minecart-Deterministic": [[14, "minecart-deterministic"]], "Minecart-Rgb": [[15, "minecart-rgb"]], "Miscellaneous": [[16, "miscellaneous"]], "MO-Ant": [[17, "mo-ant"]], "MO-Ant-2D": [[18, "mo-ant-2d"]], "MO-Halfcheetah": [[19, "mo-halfcheetah"]], "MO-Highway": [[20, "mo-highway"]], "MO-Highway-Fast": [[21, "mo-highway-fast"]], "MO-Hopper": [[22, "mo-hopper"]], "MO-Hopper-2D": [[23, "mo-hopper-2d"]], "MO-Humanoid": [[24, "mo-humanoid"]], "MO-Lunar-Lander": [[25, "mo-lunar-lander"]], "MO-Lunar-Lander-Continuous": [[26, "mo-lunar-lander-continuous"]], "MO-Mountaincar": [[27, "mo-mountaincar"]], "Reward space:": [[27, "reward-space"], [28, "reward-space"]], "MO-Mountaincarcontinuous": [[28, "mo-mountaincarcontinuous"]], "MO-Reacher": [[29, "mo-reacher"]], "MO-Supermario": [[30, "mo-supermario"]], "MO-Swimmer": [[31, "mo-swimmer"]], "MO-Walker2D": [[32, "mo-walker2d"]], "MuJoCo": [[33, "mujoco"]], "Resource-Gathering": [[34, "resource-gathering"]], "Water-Reservoir": [[35, "water-reservoir"]], "Citation": [[36, "citation"]], "MORL Baselines": [[37, "morl-baselines"]], "List of Publications": [[38, "list-of-publications"]], "API": [[39, "api"], [40, "api"]], "Install": [[39, "install"], [41, "install"]], "Citing": [[39, "citing"]], "Release Notes": [[42, "release-notes"]], "v1.1.0: MO-Gymnasium 1.1.0 Release: New MuJoCo environments, Mirrored Deep Sea Treasure, Fruit Tree rendering, and more": [[42, "release-v1-1-0"]], "v1.0.1: MO-Gymnasium 1.0.1 Release: Support Gymnasium 0.29, breakable-bottles pygame render, and more": [[42, "release-v1-0-1"]], "v1.0.0: MO-Gymnasium becomes mature": [[42, "release-v1-0-0"]], "v0.3.4: MO-Gymnasium 0.3.4 Release: Known Pareto Front, improved renders and documentation": [[42, "release-v0-3-4"]], "v0.3.3: MO-Gymnasium 0.3.3 Release: Policy Evaluation bug fix, better documentation page": [[42, "release-v0-3-3"]], "MO-Gymnasium 0.3.2 Release: Bug fixes, improved webpage": [[42, "release-0-3-2"]], "MO-Gymnasium 0.3.1 Release: Improved documentation and MuJoco MO-Reacher environment": [[42, "release-0-3-1"]], "MO-Gymnasium 0.3.0 Release: Migrate to Gymnasium": [[42, "release-0-3-0"]], "0.2.1": [[42, "release-0-2-1"]], "0.2.0": [[42, "release-0-2-0"]], "0.1.2": [[42, "release-0-1-2"]], "0.1.1": [[42, "release-0-1-1"]], "Creating a custom environment": [[43, "creating-a-custom-environment"]], "1. Create a new environment class": [[43, "create-a-new-environment-class"]], "2. Register the environment": [[43, "register-the-environment"]], "3. Test the environment": [[43, "test-the-environment"]], "4. Instantiate your environment": [[43, "instantiate-your-environment"]], "Wrappers": [[44, "wrappers"]], "LinearReward": [[44, "linearreward"]], "MONormalizeReward": [[44, "monormalizereward"]], "MOClipReward": [[44, "moclipreward"]], "MOSyncVectorEnv": [[44, "mosyncvectorenv"]], "MORecordEpisodeStatistics": [[44, "morecordepisodestatistics"]]}, "indexentries": {"linearreward (class in mo_gymnasium)": [[44, "mo_gymnasium.LinearReward"]], "moclipreward (class in mo_gymnasium)": [[44, "mo_gymnasium.MOClipReward"]], "monormalizereward (class in mo_gymnasium)": [[44, "mo_gymnasium.MONormalizeReward"]], "morecordepisodestatistics (class in mo_gymnasium)": [[44, "mo_gymnasium.MORecordEpisodeStatistics"]], "mosyncvectorenv (class in mo_gymnasium)": [[44, "mo_gymnasium.MOSyncVectorEnv"]]}}) \ No newline at end of file +Search.setIndex({"alltitles": {"0.1.1": [[45, "release-0-1-1"]], "0.1.2": [[45, "release-0-1-2"]], "0.2.0": [[45, "release-0-2-0"]], "0.2.1": [[45, "release-0-2-1"]], "1. Create a new environment class": [[46, "create-a-new-environment-class"]], "2. Register the environment": [[46, "register-the-environment"]], "3. Test the environment": [[46, "test-the-environment"]], "4. Instantiate your environment": [[46, "instantiate-your-environment"]], "404 - Page Not Found": [[0, null]], "API": [[42, null], [43, null]], "Acknowledgements": [[3, "acknowledgements"]], "Action Space": [[4, "action-space"], [6, "action-space"], [7, "action-space"], [8, "action-space"], [9, "action-space"], [10, "action-space"], [11, "action-space"], [13, "action-space"], [14, "action-space"], [15, "action-space"], [32, "action-space"], [37, "action-space"], [38, "action-space"]], "Arguments": [[4, "arguments"], [6, "arguments"], [7, "arguments"], [8, "arguments"], [9, "arguments"], [10, "arguments"], [13, "arguments"], [14, "arguments"], [15, "arguments"], [38, "arguments"]], "Breakable-Bottles": [[4, null]], "Build the Documentation": [[1, "build-the-documentation"]], "Citation": [[39, null]], "Citing": [[42, "citing"]], "Classic Control": [[5, null]], "Community": [[3, null]], "Creating a custom environment": [[46, null]], "Credits": [[4, "credits"], [6, "credits"], [7, "credits"], [8, "credits"], [9, "credits"], [10, "credits"], [13, "credits"], [14, "credits"], [15, "credits"], [37, "credits"], [38, "credits"]], "Deep-Sea-Treasure": [[6, null]], "Deep-Sea-Treasure-Concave": [[7, null]], "Deep-Sea-Treasure-Mirrored": [[8, null]], "Description": [[4, "description"], [6, "description"], [7, "description"], [8, "description"], [9, "description"], [10, "description"], [11, "description"], [13, "description"], [14, "description"], [15, "description"], [17, "description"], [18, "description"], [19, "description"], [20, "description"], [22, "description"], [23, "description"], [24, "description"], [25, "description"], [26, "description"], [32, "description"], [33, "description"], [34, "description"], [35, "description"], [37, "description"], [38, "description"]], "Episode Termination": [[4, "episode-termination"], [6, "episode-termination"], [7, "episode-termination"], [8, "episode-termination"], [10, "episode-termination"], [11, "episode-termination"], [13, "episode-termination"], [14, "episode-termination"], [15, "episode-termination"], [33, "episode-termination"], [37, "episode-termination"]], "Fishwood": [[9, null]], "Four-Room": [[10, null]], "Fruit-Tree": [[11, null]], "Grid-World": [[12, null]], "Install": [[42, "install"], [44, null]], "LinearReward": [[48, "linearreward"]], "List of Publications": [[41, null]], "MO-Ant": [[17, null]], "MO-Ant-2D": [[18, null]], "MO-Gymnasium 0.3.0 Release: Migrate to Gymnasium": [[45, "release-0-3-0"]], "MO-Gymnasium 0.3.1 Release: Improved documentation and MuJoco MO-Reacher environment": [[45, "release-0-3-1"]], "MO-Gymnasium 0.3.2 Release: Bug fixes, improved webpage": [[45, "release-0-3-2"]], "MO-Gymnasium documentation": [[1, null]], "MO-Halfcheetah": [[19, null]], "MO-Highway": [[20, null]], "MO-Highway-Fast": [[21, null]], "MO-Hopper": [[22, null]], "MO-Hopper-2D": [[23, null]], "MO-Humanoid": [[24, null]], "MO-Lunar-Lander": [[25, null]], "MO-Lunar-Lander-Continuous": [[26, null]], "MO-Mountaincar": [[27, null]], "MO-Mountaincar-3D": [[28, null]], "MO-Mountaincar-Timemove": [[29, null]], "MO-Mountaincar-Timespeed": [[30, null]], "MO-Mountaincarcontinuous": [[31, null]], "MO-Reacher": [[32, null]], "MO-Supermario": [[33, null]], "MO-Swimmer": [[34, null]], "MO-Walker2D": [[35, null]], "MOClipReward": [[48, "moclipreward"]], "MOMaxAndSkipObservation": [[48, "momaxandskipobservation"]], "MONormalizeReward": [[48, "monormalizereward"]], "MORL Baselines": [[40, null]], "MORecordEpisodeStatistics": [[47, "morecordepisodestatistics"], [48, "morecordepisodestatistics"]], "MOSyncVectorEnv": [[47, "mosyncvectorenv"]], "Minecart": [[13, null]], "Minecart-Deterministic": [[14, null]], "Minecart-Rgb": [[15, null]], "Miscellaneous": [[16, null]], "MuJoCo": [[36, null]], "Observation Space": [[4, "observation-space"], [6, "observation-space"], [7, "observation-space"], [8, "observation-space"], [9, "observation-space"], [10, "observation-space"], [11, "observation-space"], [13, "observation-space"], [14, "observation-space"], [15, "observation-space"], [32, "observation-space"], [37, "observation-space"], [38, "observation-space"]], "References": [[10, "references"]], "Release Notes": [[45, null]], "Resource-Gathering": [[37, null]], "Reward Space": [[4, "reward-space"], [6, "reward-space"], [7, "reward-space"], [8, "reward-space"], [9, "reward-space"], [10, "reward-space"], [11, "reward-space"], [13, "reward-space"], [14, "reward-space"], [15, "reward-space"], [17, "reward-space"], [18, "reward-space"], [19, "reward-space"], [20, "reward-space"], [22, "reward-space"], [23, "reward-space"], [24, "reward-space"], [25, "reward-space"], [26, "reward-space"], [32, "reward-space"], [33, "reward-space"], [34, "reward-space"], [35, "reward-space"], [37, "reward-space"], [38, "reward-space"]], "Reward space:": [[27, "reward-space"], [28, "reward-space"], [29, "reward-space"], [30, "reward-space"], [31, "reward-space"]], "Starting State": [[4, "starting-state"], [6, "starting-state"], [7, "starting-state"], [8, "starting-state"], [9, "starting-state"], [10, "starting-state"], [11, "starting-state"], [13, "starting-state"], [14, "starting-state"], [15, "starting-state"], [37, "starting-state"], [38, "starting-state"]], "Termination": [[9, "termination"]], "The requested page could not be found.": [[0, "the-requested-page-could-not-be-found"]], "Vector Wrappers": [[47, null]], "Water-Reservoir": [[38, null]], "Wrappers": [[48, null]], "v0.3.3: MO-Gymnasium 0.3.3 Release: Policy Evaluation bug fix, better documentation page": [[45, "release-v0-3-3"]], "v0.3.4: MO-Gymnasium 0.3.4 Release: Known Pareto Front, improved renders and documentation": [[45, "release-v0-3-4"]], "v1.0.0: MO-Gymnasium becomes mature": [[45, "release-v1-0-0"]], "v1.0.1: MO-Gymnasium 1.0.1 Release: Support Gymnasium 0.29, breakable-bottles pygame render, and more": [[45, "release-v1-0-1"]], "v1.1.0: MO-Gymnasium 1.1.0 Release: New MuJoCo environments, Mirrored Deep Sea Treasure, Fruit Tree rendering, and more": [[45, "release-v1-1-0"]], "v1.2.0: MO-Gymnasium 1.2.0 Release: Update Gymnasium to v1.0.0, New Mountaincar Environments, Documentation and Test Improvements, and more": [[45, "release-v1-2-0"]]}, "docnames": ["404", "README", "citing/citing", "community/community", "environments/breakable-bottles", "environments/classical", "environments/deep-sea-treasure", "environments/deep-sea-treasure-concave", "environments/deep-sea-treasure-mirrored", "environments/fishwood", "environments/four-room", "environments/fruit-tree", "environments/grid-world", "environments/minecart", "environments/minecart-deterministic", "environments/minecart-rgb", "environments/misc", "environments/mo-ant", "environments/mo-ant-2d", "environments/mo-halfcheetah", "environments/mo-highway", "environments/mo-highway-fast", "environments/mo-hopper", "environments/mo-hopper-2d", "environments/mo-humanoid", "environments/mo-lunar-lander", "environments/mo-lunar-lander-continuous", "environments/mo-mountaincar", "environments/mo-mountaincar-3d", "environments/mo-mountaincar-timemove", "environments/mo-mountaincar-timespeed", "environments/mo-mountaincarcontinuous", "environments/mo-reacher", "environments/mo-supermario", "environments/mo-swimmer", "environments/mo-walker2d", "environments/mujoco", "environments/resource-gathering", "environments/water-reservoir", "examples/citation", "examples/morl_baselines", "examples/publications", "index", "introduction/api", "introduction/install", "release_notes", "tutorials/custom_env", "wrappers/vector_wrappers", "wrappers/wrappers"], "envversion": {"sphinx": 62, "sphinx.domains.c": 3, "sphinx.domains.changeset": 1, "sphinx.domains.citation": 1, "sphinx.domains.cpp": 9, "sphinx.domains.index": 1, "sphinx.domains.javascript": 3, "sphinx.domains.math": 2, "sphinx.domains.python": 4, "sphinx.domains.rst": 2, "sphinx.domains.std": 2}, "filenames": ["404.md", "README.md", "citing/citing.md", "community/community.md", "environments/breakable-bottles.md", "environments/classical.md", "environments/deep-sea-treasure.md", "environments/deep-sea-treasure-concave.md", "environments/deep-sea-treasure-mirrored.md", "environments/fishwood.md", "environments/four-room.md", "environments/fruit-tree.md", "environments/grid-world.md", "environments/minecart.md", "environments/minecart-deterministic.md", "environments/minecart-rgb.md", "environments/misc.md", "environments/mo-ant.md", "environments/mo-ant-2d.md", "environments/mo-halfcheetah.md", "environments/mo-highway.md", "environments/mo-highway-fast.md", "environments/mo-hopper.md", "environments/mo-hopper-2d.md", "environments/mo-humanoid.md", "environments/mo-lunar-lander.md", "environments/mo-lunar-lander-continuous.md", "environments/mo-mountaincar.md", "environments/mo-mountaincar-3d.md", "environments/mo-mountaincar-timemove.md", "environments/mo-mountaincar-timespeed.md", "environments/mo-mountaincarcontinuous.md", "environments/mo-reacher.md", "environments/mo-supermario.md", "environments/mo-swimmer.md", "environments/mo-walker2d.md", "environments/mujoco.md", "environments/resource-gathering.md", "environments/water-reservoir.md", "examples/citation.md", "examples/morl_baselines.md", "examples/publications.md", "index.md", "introduction/api.md", "introduction/install.md", "release_notes.md", "tutorials/custom_env.md", "wrappers/vector_wrappers.md", "wrappers/wrappers.md"], "indexentries": {"linearreward (class in mo_gymnasium.wrappers)": [[48, "mo_gymnasium.wrappers.LinearReward", false]], "moclipreward (class in mo_gymnasium.wrappers)": [[48, "mo_gymnasium.wrappers.MOClipReward", false]], "momaxandskipobservation (class in mo_gymnasium.wrappers)": [[48, "mo_gymnasium.wrappers.MOMaxAndSkipObservation", false]], "monormalizereward (class in mo_gymnasium.wrappers)": [[48, "mo_gymnasium.wrappers.MONormalizeReward", false]], "morecordepisodestatistics (class in mo_gymnasium.wrappers)": [[48, "mo_gymnasium.wrappers.MORecordEpisodeStatistics", false]], "morecordepisodestatistics (class in mo_gymnasium.wrappers.vector)": [[47, "mo_gymnasium.wrappers.vector.MORecordEpisodeStatistics", false]], "mosyncvectorenv (class in mo_gymnasium.wrappers.vector)": [[47, "mo_gymnasium.wrappers.vector.MOSyncVectorEnv", false]]}, "objects": {"mo_gymnasium.wrappers": [[48, 0, 1, "", "LinearReward"], [48, 0, 1, "", "MOClipReward"], [48, 0, 1, "", "MOMaxAndSkipObservation"], [48, 0, 1, "", "MONormalizeReward"], [48, 0, 1, "", "MORecordEpisodeStatistics"]], "mo_gymnasium.wrappers.vector": [[47, 0, 1, "", "MORecordEpisodeStatistics"], [47, 0, 1, "", "MOSyncVectorEnv"]]}, "objnames": {"0": ["py", "class", "Python class"]}, "objtypes": {"0": "py:class"}, "terms": {"": [4, 5, 6, 7, 8, 10, 13, 14, 15, 16, 17, 18, 19, 22, 23, 24, 25, 26, 27, 28, 29, 30, 34, 35, 42, 43, 45, 48], "0": [4, 6, 7, 8, 9, 10, 11, 13, 14, 15, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 37, 38, 42, 43, 47, 48], "01": 45, "02": 45, "03": 45, "06": 45, "07": [27, 28, 29, 30, 31], "08": [45, 48], "09": 45, "1": [4, 6, 7, 8, 9, 10, 11, 13, 14, 15, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 37, 38, 47, 48], "10": [6, 7, 8, 11, 12, 25, 26, 37, 38, 45], "100": [25, 26, 33, 45, 47, 48], "101": 45, "103": 45, "105": 45, "106": 45, "107": 45, "11": [6, 7, 22, 23, 45], "1109": 38, "1145": 37, "12": 45, "124": [7, 8], "13": [10, 45], "1390156": 37, "1390162": 37, "14": [10, 45], "16": 45, "160": 38, "17": [19, 24, 35], "18": 45, "19": 45, "1e": [34, 48], "2": [4, 6, 7, 8, 9, 11, 13, 14, 15, 17, 18, 19, 20, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 37, 38, 42, 43, 47], "20": [8, 45], "200": 9, "2008": [12, 37], "2010": 12, "2011": 5, "2012": 38, "2013": 16, "2017": 10, "2018": 12, "2019": [6, 7, 8, 11, 12, 13, 14, 15, 16], "2020": 36, "2021": 12, "2022": [2, 5, 12, 41, 45], "2022bnaic": 2, "2023": [39, 41, 42, 45], "2024": [41, 45], "21": 45, "23": [6, 45], "24": 45, "240": [4, 33], "25": [33, 45], "255": [15, 33], "256": 33, "25th": 37, "26": 45, "27": [17, 18, 45], "28": [25, 26], "2d": [6, 7, 8, 10, 13, 14, 15, 31, 45, 47], "3": [4, 6, 7, 8, 10, 13, 14, 15, 17, 18, 20, 21, 22, 23, 25, 26, 27, 28, 29, 30, 32, 33, 37, 38, 47], "30": 45, "31": 45, "33": 45, "34": 45, "34th": 2, "35": 45, "360": 4, "37": 45, "376": 24, "37th": [39, 42], "3d": [5, 13, 14, 15, 27, 29, 30], "4": [4, 6, 7, 8, 10, 13, 14, 15, 24, 25, 26, 32, 33, 34, 37, 38, 47, 48], "40": 45, "41": [37, 45], "42": [45, 47], "43": 45, "45": 45, "46": 45, "47": [37, 45], "480": 15, "5": [4, 11, 12, 13, 14, 15, 20, 21, 25, 26, 33, 37, 45], "50": [4, 45], "51": 45, "52": 45, "53": 45, "55": 45, "56": 45, "57": 45, "58": 45, "59": 45, "6": [11, 12, 13, 14, 15, 19, 25, 26, 27, 28, 29, 30, 31, 32, 35], "60": 45, "61": 45, "62": 45, "6252759": 38, "63": 11, "64": 45, "65": 45, "67": 45, "69": 45, "7": [6, 11, 12, 13, 14, 15, 45, 47], "70": 45, "72": 45, "73": 45, "74": 45, "75": 45, "76": 45, "77": 45, "79": 45, "8": [17, 18, 25, 26, 34, 38, 42, 43, 45], "80": 45, "81": 45, "83": 45, "84": 45, "86": 45, "87": 45, "89": 45, "9": 32, "90": 45, "91": 45, "92": 45, "93": 45, "94": 45, "95": 45, "97": 45, "99": [45, 48], "A": [2, 4, 10, 16, 17, 18, 21, 27, 28, 29, 30, 31, 38, 39, 41, 42, 43, 48], "As": [4, 42, 43], "At": 47, "But": 48, "By": [27, 28, 29, 30, 38], "For": [1, 32, 42, 43, 45, 47], "If": [3, 13, 14, 15, 17, 18, 22, 23, 38, 39, 42, 46], "In": [4, 45], "It": [40, 42, 43, 45, 46], "Of": 45, "The": [3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 22, 23, 24, 25, 26, 31, 32, 33, 34, 35, 37, 38, 42, 45, 46, 47], "There": 38, "To": [1, 6, 7, 8, 42, 44], "With": 45, "_": 47, "__init__": 46, "_build": 1, "_episod": 47, "_forward_reward_weight": 45, "_modul": 48, "aama": 41, "abel": [13, 14, 15, 16], "about": [1, 5], "abov": 4, "acceler": [13, 14, 15], "accept": 45, "access": [45, 47], "account": [4, 12], "achiev": 45, "act": [42, 43, 45], "action": [5, 12, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 33, 34, 35, 36, 45, 46, 47], "action_spac": [46, 47], "acttyp": 48, "ad": [17, 18, 22, 23, 45, 46, 47], "adapt": [6, 7, 8, 10], "add": [27, 28, 29, 30, 41, 45], "add_speed_object": [27, 28, 29, 30], "addit": 5, "addition": 45, "after": [9, 45, 48], "again": 4, "agent": [4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 37, 38, 45], "ai": 4, "al": [5, 6, 7, 8, 10, 11, 12, 13, 14, 15, 16, 36, 41], "alegr": [2, 12, 39, 41, 42], "algorithm": [40, 42], "align": 41, "all": [3, 17, 18, 37, 42, 44, 45, 47, 48], "allow": 45, "also": [3, 16, 42, 43, 45], "altern": [27, 28, 29, 30], "alwai": [6, 7, 8], "amount": [16, 38], "amp": 45, "an": [5, 10, 27, 28, 29, 30, 33, 37, 38, 42, 43, 45, 46, 48], "ana": [2, 39, 42], "andrea": 45, "andr\u00e9": 10, "angl": 32, "angular": 32, "ani": 47, "ann": [2, 39, 42], "ansi": 38, "ansimuz": [6, 7, 8], "ant": 36, "antenv": [17, 18], "api": [40, 45, 46], "appear": 2, "appli": [4, 32, 47], "approach": 4, "approxim": 41, "ar": [3, 4, 13, 14, 15, 16, 37, 38, 45, 46, 47, 48], "arm": 32, "arrai": [10, 17, 18, 19, 22, 23, 34, 42, 43, 45, 46, 47, 48], "art": [4, 6, 7, 8, 45], "artifici": 2, "asid": 3, "ask": 3, "asset": [4, 37, 45], "assist": [4, 6, 7, 8], "associ": 45, "atari_wrapp": 48, "attribut": 46, "australia": 38, "author": [2, 39, 42], "autobuild": 1, "automat": [1, 45, 46], "avail": [45, 47, 48], "averag": 48, "avoid": [10, 16], "axel": [13, 14, 15], "axelabel": 3, "axi": [22, 23], "b": 1, "back": 45, "background": [6, 7, 8, 38], "backward": 5, "balanc": 45, "barret": 12, "barreto": 10, "barrett": 37, "base": [3, 4, 13, 14, 15, 32, 36, 38, 41, 45, 48], "baselin": 45, "baselines3": 48, "batteri": 45, "bazzan": [2, 39, 42], "becaus": 4, "been": [4, 5, 45], "befor": 47, "begin": [47, 48], "behind": 5, "benchmark": [39, 41, 42], "benefit": 45, "benelearn": 2, "benelux": 2, "between": [33, 38, 42, 45, 48], "bib": 45, "binari": [10, 11, 12], "blob": [13, 14, 15], "blue": 10, "bnaic": [2, 41], "bnj6kubtg6": 42, "booktitl": [2, 39, 42], "bool": 47, "boolean": [4, 47], "both": 48, "both_norm_env": 48, "bottl": 12, "bottle_reward": 4, "bottles_carri": 4, "bottles_deliv": [4, 12], "bottles_drop": 4, "bound": [38, 45], "box": [6, 7, 8, 17, 18, 19, 22, 23, 24, 26, 31, 34, 35, 38], "brake": [13, 14, 15], "break": 45, "breakabl": 12, "breakablebottl": 4, "brisban": 38, "bro": 33, "bruno": [2, 39, 42], "budget": 41, "buffer": 47, "buffer_length": [47, 48], "bugfix": 45, "bump": 45, "button": 45, "c": [2, 39, 42], "cai": 41, "calcul": 4, "call": 45, "callabl": 47, "can": [3, 4, 9, 11, 13, 14, 15, 27, 28, 29, 30, 38, 42, 43, 44, 45, 47, 48], "cannot": 4, "capabl": 45, "capac": [13, 14, 15], "car": [5, 27, 28, 29, 30, 45], "carb": [11, 12], "care": 47, "carri": 4, "cart": [13, 14, 15], "castelletti": 38, "catch": 9, "caus": 45, "cc": 45, "cd": 1, "cell": 12, "central": 32, "certain": [42, 44], "chanc": 12, "chang": [1, 6, 7, 8, 27, 28, 29, 30, 45], "changelog": 45, "check": [42, 43, 45], "chose": 11, "ci": 45, "circl": 10, "citat": 45, "cite": 39, "class": [5, 42, 43, 47, 48], "classic": [6, 7, 8, 46], "clip": 48, "close": 46, "co": [13, 14, 15, 32], "code": [3, 6, 7, 8, 9, 10, 13, 14, 15, 38, 45, 48], "coin": [16, 33], "colab": [42, 43], "collect": [9, 10, 11, 12, 13, 14, 15, 16, 33, 37, 45], "collis": [16, 20], "com": [3, 13, 14, 15], "combin": 45, "commit": 45, "common": 48, "commun": [42, 45], "compar": 42, "complet": 48, "compliant": 42, "compon": [10, 45, 48], "compromis": 45, "comput": [32, 45, 46], "concav": [12, 45], "concave_map": [6, 7, 8], "conduct": 45, "confer": [2, 37, 38, 39, 42], "config": [13, 14, 15], "configur": [13, 14, 15], "conflict": 45, "conor": 3, "consequ": 45, "consist": 37, "constructor": 46, "consum": [13, 14, 15], "consumpt": [5, 13, 14, 15, 16], "contain": [1, 4, 10, 11, 12, 13, 14, 15, 27, 28, 29, 30, 31, 32, 40], "content": 38, "context": 45, "continu": [5, 6, 7, 8, 16, 31, 36, 38, 45], "contribut": [1, 3, 4, 45], "contributor": [3, 45], "control": [6, 7, 8, 9, 17, 18, 19, 22, 23, 24, 34, 35], "control_cost": 45, "converg": 5, "convers": 45, "convex": [6, 7, 8], "coordin": [6, 7, 8, 37, 42], "copi": 47, "corner": [13, 14, 15], "correct": 45, "correspond": [16, 27, 28, 29, 30, 38], "cost": [17, 18, 19, 22, 23, 24, 25, 26, 34, 35, 38], "cost_flood": 16, "cost_object": [17, 18, 22, 23], "crash": [25, 26], "creat": [4, 6, 7, 8, 42, 43, 45], "creation": 45, "criteria": 37, "ctrl_cost": 45, "cumul": [47, 48], "current": [4, 6, 7, 8, 38], "custom": 45, "d": [11, 12, 41], "da": [2, 39, 42], "dall": [4, 6, 7, 8], "dam": [16, 38], "danoi": [2, 39, 42], "deal": 46, "death": 16, "decis": 38, "decomposit": 41, "deep": [3, 12, 47, 48], "deep_sea_treasur": 45, "deepseatreasur": [6, 7, 8], "default": [6, 7, 8, 13, 14, 15, 27, 28, 29, 30, 38], "deficit": 38, "deficit_wat": 16, "defin": [4, 5, 16, 32, 46], "definit": [42, 43], "deliv": [4, 12], "demand": 38, "deni": [3, 9], "dens": [13, 14, 15], "depend": [42, 44], "deprec": 45, "depth": [11, 12], "deque_s": 47, "descript": [5, 12, 16, 36], "design": [45, 47], "desir": 45, "destin": 12, "detail": [5, 42, 43], "determin": 45, "determinist": 45, "develop": 42, "deviat": 48, "di": 33, "diamond": 37, "dict": 4, "dictionari": [4, 12], "did": 4, "differ": [4, 12, 45], "dim_reward": 47, "dimens": [4, 45], "dimension": [6, 7, 8, 9, 10, 11, 13, 14, 15, 17, 18, 19, 20, 22, 23, 24, 25, 26, 32, 33, 34, 35, 37], "directli": [45, 47, 48], "directori": 46, "dirhtml": 1, "disc_episode_return": 45, "discord": [3, 42], "discount": [46, 47, 48], "discret": [4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 20, 21, 25, 27, 28, 29, 30, 32, 33, 36, 37, 45], "dissert": 5, "distanc": [32, 46], "distinct": 45, "distribut": 41, "do": 45, "doc": [1, 45], "document": [42, 46], "doe": [42, 44, 48], "doi": 38, "domain": 45, "done": [46, 47], "dot": 48, "down": [6, 7, 8, 10, 37], "downstream": 38, "dr": [47, 48], "drop": [4, 45], "dst": [12, 45], "dst_map": [6, 7, 8], "dtype": [45, 47], "due": [5, 38], "dynmorl": 3, "e": [1, 2, 4, 6, 7, 8, 12, 31, 39, 42, 45], "each": [4, 6, 7, 8, 11, 13, 14, 15, 27, 28, 29, 30, 31, 32, 45, 47], "eat": 12, "edit": 45, "effici": 41, "either": 9, "el": [2, 39, 42], "elaps": [47, 48], "elbow": 32, "element": [37, 45], "els": [10, 33, 37], "en": 48, "enabl": 45, "end": [9, 13, 14, 15, 47], "enemi": [4, 12, 16, 33, 37], "energi": 36, "engin": [25, 26], "entri": 41, "entry_point": 46, "env": [3, 5, 12, 13, 14, 15, 16, 17, 18, 19, 20, 22, 23, 24, 25, 26, 27, 28, 29, 30, 34, 35, 36, 42, 43, 45, 46, 47, 48], "env_fn": 47, "environ": [2, 4, 5, 6, 7, 8, 9, 10, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 38, 41, 42, 43, 44, 47], "episod": [9, 38, 47, 48], "epsilon": 48, "equival": 5, "error": 45, "esr": [12, 45], "essenti": [42, 46], "et": [5, 6, 7, 8, 10, 11, 12, 13, 14, 15, 16, 36, 41], "eval_mo": 45, "everi": [1, 11, 12, 48], "exampl": [10, 40, 42, 43, 45, 47, 48], "except": 48, "excess": 38, "execut": [16, 38], "exhaust": 45, "expand": 45, "expect": 9, "extend": 45, "extra": [5, 27, 28, 29, 30], "extract": 48, "ezpickl": 45, "f": [3, 38], "fair": 41, "fall": 45, "fals": [17, 18, 22, 23, 47], "famili": [42, 44], "fan": 41, "fantasi": [6, 7, 8], "far": 33, "farama": [3, 13, 14, 15, 42, 45], "fast": [16, 45], "fat": [11, 12], "featur": [3, 10, 45], "feder": 41, "felten": [2, 12, 39, 41, 42], "felten_toolkit_2023": [39, 42], "few": [45, 47, 48], "ffelten": 45, "file": [13, 14, 15, 45, 46], "fill": [13, 14, 15], "finger_tip_coord": 32, "fire": 12, "first": [2, 13, 14, 15, 38, 41, 45, 47], "fish": [9, 12], "fish_amount": 12, "fisherman": 9, "fishproba": 9, "fishwood": [3, 12, 45], "fit": 38, "fix": 10, "flag": [4, 17, 18, 22, 23, 33, 37, 46], "flexibl": 45, "float": [38, 46, 47, 48], "float32": [17, 18, 19, 22, 23, 24, 26, 31, 34, 35, 38, 47], "float_stat": [6, 7, 8], "flood": 38, "florian": [2, 39, 42], "folder": [1, 45], "follow": [2, 10, 13, 14, 15, 17, 18, 19, 22, 23, 27, 28, 29, 30, 34, 42, 43, 45, 46], "forgotten": 45, "fork": 1, "form": 47, "formerli": [2, 41], "forward": [5, 19, 22, 23, 24, 27, 28, 29, 30, 34, 35], "forward_penalti": 5, "forward_reward": 45, "found": 45, "foundat": [13, 14, 15, 45], "four": [3, 12, 32], "frame": 48, "frame_skip": [13, 14, 15], "frameskip": 48, "framework": 41, "from": [3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 37, 38, 45, 46, 47, 48], "front": 46, "fruit": [3, 12], "fruit_tre": 45, "fuel": [5, 13, 14, 15, 16, 25, 26, 31], "fuel_consumption_penalti": 5, "full": [11, 12, 45], "function": [42, 43, 45], "g": [10, 12, 45], "gamma": [46, 47, 48], "gather": [12, 45], "gem": [4, 12, 37], "gener": [41, 45, 46], "get": 45, "gg": 42, "ghazali": [2, 39, 42], "gif": 45, "gimelfarb": [3, 10], "github": [3, 13, 14, 15, 45], "give": 5, "given": 48, "go": [1, 9, 11, 22, 23, 27, 28, 29, 30], "goal": [10, 12, 27, 28, 29, 30, 31], "goe": 46, "goir": [2, 39, 42], "gold": [4, 12, 37], "gr": [2, 39, 42], "green": 10, "grid": [6, 7, 8], "gridworld": [10, 12], "ground": 4, "group": 45, "gt": 45, "guarante": 41, "guid": [42, 43], "gupta": 5, "gym": [2, 33, 41, 42, 43, 45], "gymnasium": [2, 5, 13, 14, 15, 16, 17, 18, 19, 22, 23, 24, 25, 26, 27, 28, 29, 30, 34, 35, 40, 41, 42, 43, 44, 46, 47, 48], "ha": [4, 5, 33, 45, 47], "halfcheetah": [36, 45], "halfcheetahenv": 19, "harder": 12, "hartmann": 41, "have": [3, 4, 5, 12, 42, 45, 48], "hay": 3, "healthi": [17, 18], "heavili": 48, "height": 36, "help": 3, "here": [3, 10, 42, 43, 45], "high": [4, 6, 7, 8, 9, 10, 11, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 37, 38, 45], "higher": 45, "highwai": [16, 45], "highwayenv": 20, "highwayfastenv": 21, "home": [4, 37], "hopper": [36, 45], "hopperenv": [22, 23], "hotfix": 45, "how": [1, 13, 14, 15, 33, 40, 45], "html": 48, "http": [3, 4, 6, 7, 8, 13, 14, 15, 37, 38, 42, 48], "human": [13, 14, 15, 38], "humanoid": 36, "humanoidenv": 24, "humonoid": 36, "hung": 5, "hydroelectr": 38, "hyperparamet": 41, "i": [1, 3, 4, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 37, 38, 40, 42, 43, 45, 46, 47, 48], "ianleongudri": 45, "id": 46, "idx": 48, "igd": 46, "ijcnn": 38, "illustr": 45, "imag": [13, 14, 15, 16, 38], "image_observ": [13, 14, 15], "impact": 4, "implement": [4, 40, 46], "import": [4, 6, 7, 8, 9, 10, 11, 13, 14, 15, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 37, 38, 42, 43, 45, 46, 47, 48], "improv": 41, "includ": [16, 42, 44], "inconsist": 45, "increment": [13, 14, 15], "incremental_frame_skip": [13, 14, 15], "index": [47, 48], "indic": [4, 10, 37, 45, 47], "inf": [4, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 32, 33, 34, 35, 38], "info": [42, 43, 45, 46, 47, 48], "info_dict": 45, "inform": [1, 13, 14, 15, 17, 18, 19, 20, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 33, 34, 35, 39, 42], "inher": 45, "inherit": 46, "init": 45, "initi": [38, 46], "initial_st": 38, "inproceed": [2, 39, 42], "inspir": 48, "instal": 1, "instanc": [42, 43, 45], "instead": [4, 45], "int": [47, 48], "int32": 47, "integ": 46, "integr": 45, "intellig": 2, "interact": [42, 43], "intern": [37, 38], "introduc": [5, 10, 45], "invert": 46, "io": [4, 6, 7, 8, 37, 48], "issu": 45, "itch": [4, 6, 7, 8, 37], "item": [10, 12], "item1": 12, "item2": 12, "item3": 12, "iter": [38, 47], "its": 46, "ivanov": 41, "j": 45, "johnson": 45, "join": [3, 42], "joint": [32, 38], "json": [13, 14, 15], "jump": [22, 23], "kallinteri": 45, "katze2664": 45, "keep": [47, 48], "kei": [4, 47], "kill": [12, 33, 37], "klassert": 4, "known": 46, "kwarg": 46, "l": [2, 39, 42, 47, 48], "lack": 5, "lambda": 47, "land": [5, 25, 26], "lander": [5, 45], "lane": [16, 20], "larger": 4, "last": [47, 48], "leaf": [11, 12], "learn": [2, 4, 9, 10, 37, 39, 41, 42, 43, 45], "left": [4, 6, 7, 8, 10, 11, 13, 14, 15, 37], "length": [47, 48], "length_queu": 47, "leon": 37, "level": [38, 45], "leverag": 41, "librari": [2, 41, 42, 45], "life": 45, "light": 12, "like": [3, 42, 44, 48], "limezu": [4, 37], "limit": 16, "line": 46, "linear": [17, 18, 19, 22, 23, 34], "linearli": 45, "linearreward": [17, 18, 19, 22, 23, 34, 42, 43, 45], "linearwrapp": 45, "link": 45, "lint": 45, "list": [4, 45], "literatur": 45, "local": 5, "locat": [4, 12, 32], "logo": 45, "look": 48, "low": [4, 6, 7, 8, 9, 10, 11, 13, 14, 15, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 37, 38], "lower": 10, "luca": [2, 39, 42], "lucasalegr": 45, "lunar": [5, 45], "lunarland": [5, 25, 26], "m": 38, "machin": 37, "made": [1, 45], "mai": 45, "main": [3, 13, 14, 15, 25, 26], "main_engine_fuel": 5, "make": [1, 4, 6, 7, 8, 9, 10, 11, 13, 14, 15, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 37, 38, 42, 43, 45, 46, 47, 48], "mani": [13, 14, 15, 47], "map": [6, 7, 8, 10, 12, 13, 14, 15, 45], "mario": [33, 45], "mark": 45, "markov": 38, "master": 48, "match": 45, "mathieu": [3, 38], "max": 48, "max_r": 48, "max_t": 9, "maxandskipenv": 48, "maxima": 5, "maximum": 38, "maze": 10, "md": [1, 45], "mdp": [42, 43, 45], "mean": 48, "merg": [5, 27, 28, 29, 30], "merge_move_penalti": [27, 28, 29, 30], "method": [45, 46], "metric": 46, "mgoulao": 45, "mike": [3, 10], "min": 48, "min_r": 48, "mine": [13, 14, 15], "mine_config": [13, 14, 15], "minecart": [3, 16, 42, 43, 45], "miner": [11, 12], "minerium": [13, 14, 15], "minim": [13, 14, 15, 16], "minor": 45, "mirror": 12, "mirrored_map": [6, 7, 8], "miss": [41, 45], "mistak": 45, "mo": [2, 3, 5, 13, 14, 15, 16, 36, 40, 41, 42, 43, 44, 46, 47, 48], "mo_gym": [17, 18, 19, 22, 23, 34, 42, 43, 45, 47, 48], "mo_gymnasium": [4, 6, 7, 8, 9, 10, 11, 13, 14, 15, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 37, 38, 42, 43, 45, 46, 47, 48], "mode": [13, 14, 15, 38], "model": [41, 42, 43], "modem": 41, "modifi": 45, "modul": [47, 48], "mofl": 41, "momaxandskipobserv": 45, "momdp": [42, 43, 45], "monormalizereward": 45, "more": [1, 5, 13, 14, 15, 17, 18, 19, 20, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 33, 34, 35, 42, 43], "morecordepisodestatist": 45, "moreov": [46, 47], "morewordstatist": 47, "morl": [3, 6, 7, 8, 9, 42, 43, 45], "most": 47, "mountain": [5, 27, 28, 29, 30, 31, 45], "mountaincar": [5, 31], "mountaincarcontinu": [5, 45], "move": [4, 5, 33, 34, 37, 45, 48], "move_penalti": 5, "much": 33, "mujoco": [42, 44], "multi": [2, 5, 9, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 32, 33, 34, 35, 36, 38, 39, 41, 42, 43, 45, 46], "multibinari": 4, "multiobject": 4, "multipl": [4, 37, 40, 41, 45, 46, 47], "must": [12, 13, 14, 15, 16, 46], "my_env_dir": 46, "my_env_fil": 46, "my_env_v0": 46, "myenv": 46, "mypi": 45, "n": [2, 39, 42], "nO": 38, "narayanan": [12, 37], "ndarrai": 48, "need": 45, "neg": [10, 31, 32], "neighbour": 16, "network": 38, "neural": [38, 39, 42], "neurip": [39, 41, 42], "next": 46, "next_ob": [42, 43, 45], "ninjikin": [4, 37], "nip": 10, "node": 11, "none": [13, 14, 15, 38, 45, 48], "norm": 31, "norm_treasure_env": 48, "normal": [38, 45, 47, 48], "normalized_act": 38, "note": [4, 48], "notebook": [42, 43], "now": [2, 39, 42, 45], "np": [17, 18, 19, 22, 23, 34, 42, 43, 45], "num": 47, "num_env": 47, "number": [4, 38], "numpi": [42, 43, 45, 46], "nutri1": 12, "nutri6": 12, "nutrient": [11, 12], "ob": [5, 12, 16, 36, 42, 43, 45, 47], "object": [2, 5, 9, 12, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 32, 33, 34, 35, 36, 38, 39, 41, 42, 43, 45, 46], "observ": [12, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 33, 34, 35, 45, 46, 48], "observation_spac": 46, "observationspac": 45, "obstyp": 48, "off": 45, "oject": 46, "onc": 1, "one": [42, 44, 45, 48], "onli": [38, 48], "open": [41, 42], "opengameart": 38, "optim": [37, 41, 45], "option": [27, 28, 29, 30, 42, 43, 45, 46], "order": 45, "ore1": 16, "ore2": 16, "ores": [13, 14, 15, 16], "org": [38, 42], "orient": [13, 14, 15], "origin": [4, 17, 18, 19, 22, 23, 34, 42, 43, 45], "other": [16, 17, 18, 22, 23, 42, 43, 45, 48], "otherwis": [4, 9, 33], "our": [1, 45, 46], "out": [3, 38], "outcom": 4, "output": 47, "packag": [1, 45], "paper": 4, "pareto": [41, 46], "pareto_front": [45, 46], "parisi": 38, "part": [45, 46], "pass": [33, 45], "passag": 10, "path": [13, 14, 15], "paulina": 38, "penal": 38, "penalti": [4, 5, 6, 7, 8, 12, 27, 28, 29, 30, 31, 33], "peopl": 3, "percentag": 38, "perform": [45, 46], "person": 41, "pf": 45, "pianosi": [16, 38], "pick": 4, "pip": [1, 42, 44], "pixel": [4, 6, 7, 8, 45], "plan": [42, 43], "pleas": [39, 41, 42], "plu": 10, "point": 33, "polici": [37, 41], "porcentag": [13, 14, 15], "port": 38, "posit": [5, 6, 7, 8, 10, 13, 14, 15, 32, 33, 37], "possibl": [4, 32], "potenti": [4, 12, 45], "pp": 38, "practic": [42, 43], "pranav": 5, "pranavg23": 45, "pre": 45, "predefin": 45, "prefer": 45, "prevent": 5, "previous": 45, "priorit": 41, "prob_drop": 4, "probabl": [4, 9], "problem": [4, 6, 7, 8, 9, 38, 45], "problemat": [42, 44], "proceed": [2, 37, 39, 42], "process": [39, 42], "product": 48, "project": 3, "protein": [11, 12], "provid": [3, 9, 42, 45, 47], "pseudo": 45, "public": [2, 42], "publish": 41, "pull": [41, 46], "py": [45, 46], "pydoc": 45, "pypi": 45, "pytest": 46, "python": [42, 43, 45], "q": 38, "qld": 38, "qualiti": 45, "quantiti": [13, 14, 15], "question": 3, "r": [1, 47, 48], "r_i": 32, "randint": 45, "random": 38, "rang": [45, 47], "rather": 4, "reach": [3, 6, 7, 8, 10, 11, 12, 16, 27, 28, 29, 30, 31, 33, 45], "reacher": 36, "read": 5, "readm": 45, "readthedoc": 48, "reason": 5, "rebuild": 1, "receiv": [11, 45], "recent": 47, "recov": [17, 18, 19, 22, 23, 34], "red": 10, "refactor": [3, 13, 14, 15], "refer": 46, "registr": 46, "registri": 46, "reinforc": [2, 4, 9, 10, 39, 41, 42, 43, 45], "reinject": 48, "relax": [2, 39, 42], "releas": [16, 38], "reli": 45, "reliabl": [39, 41, 42], "remov": [27, 28, 29, 30], "remove_move_penalti": [27, 28, 29, 30], "renam": 45, "render": [13, 14, 15, 38, 46], "render_mod": [13, 14, 15, 38], "repeat": [13, 14, 15], "repositori": [39, 40, 42, 46], "repres": 45, "request": 41, "requir": 1, "research": [39, 41, 42], "reservoir": [3, 16, 45], "reset": [42, 43, 45, 46, 47, 48], "resourc": [12, 45], "respect": 47, "restelli": 38, "retriev": [13, 14, 15], "return": [9, 13, 14, 15, 37, 42, 45, 46, 48], "return_queu": 47, "revamp": 45, "revers": [4, 5, 27, 28, 29, 30], "reverse_penalti": 5, "reward": [5, 21, 42, 43, 45, 46, 47, 48], "reward_dim": 46, "reward_spac": [45, 46], "reymond": [3, 38], "rgb": [13, 14], "rgb_arrai": [13, 14, 15, 38], "right": [4, 6, 7, 8, 10, 11, 13, 14, 15, 20, 37], "right_lan": 16, "rightest": 16, "riva": 38, "rl": 45, "rnd": 45, "robert": 4, "rodriguez": 41, "roijer": 12, "room": [3, 12], "root": [11, 45], "run": [19, 24, 35, 46, 47], "runzheyang": 3, "safeti": 4, "same": [6, 7, 8], "sampl": [41, 47], "save": 45, "scalar": [17, 18, 19, 22, 23, 34, 42, 43, 45, 48], "scenario": 45, "scott": 45, "sea": [3, 12, 47, 48], "sebimarkgraf": 45, "second": [13, 14, 15], "section": 4, "see": [10, 13, 14, 15, 17, 18, 19, 20, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 33, 34, 35, 42, 43, 45, 46], "seed": [46, 47], "select": 38, "self": [45, 46], "sens": 48, "separ": 10, "serenevillagerevamp": [4, 37], "serial": 47, "server": [3, 42], "set": [17, 18, 22, 23, 42, 45, 46], "setup": 45, "shape": [4, 6, 7, 8, 9, 10, 11, 13, 14, 15, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 37, 38, 46, 47], "shaped_reward": 5, "should": [45, 46], "shown": 45, "side": [25, 26], "side_engine_fuel": 5, "signal": 5, "silva": [2, 39, 42], "similar": [36, 45, 47], "similarli": [5, 16], "simon": 38, "simpl": [9, 42, 43], "simpli": 3, "sin": [13, 14, 15, 32], "sinc": [46, 47, 48], "singl": [27, 28, 29, 30, 45], "size": [4, 11, 46], "skip": 48, "sky": 38, "small": [4, 45], "smooth": 48, "snippet": 45, "so": 4, "some": [3, 42, 44, 46], "soto": 41, "sourc": [6, 7, 8, 10, 12, 13, 14, 15, 31, 42], "space": [5, 12, 16, 21, 36, 45, 46], "spars": [13, 14, 15], "specif": 47, "specifi": 4, "speed": [5, 13, 14, 15, 16, 20, 27, 28, 29, 30, 45], "speed_object": 5, "spell": 45, "sphinx": 1, "split": 10, "squar": 10, "srini": 37, "stabil": 48, "stabl": [45, 48], "stable_baselines3": 48, "stai": 16, "standard": [42, 45, 48], "static": 5, "statist": 47, "stats_kei": [47, 48], "steckelmach": [3, 9], "step": [4, 5, 6, 7, 8, 9, 27, 28, 29, 30, 31, 33, 38, 41, 42, 43, 45, 46, 47], "store": 47, "str": [47, 48], "structur": 45, "sub": 47, "submarin": [6, 7, 8, 12], "submiss": 41, "subpackag": 45, "successfulli": [25, 26], "successor": [3, 10], "suit": 42, "super": 33, "supermario": [3, 16], "supermariobro": 33, "supermariobrosenv": 16, "suppli": 38, "support": 16, "swimmer": 36, "swimmerenv": 34, "system": [39, 42, 44], "t": [47, 48], "tailor": 45, "take": [4, 12], "taken": 12, "talbi": [2, 39, 42], "target": 32, "target_1": 36, "target_2": 36, "target_3": 36, "target_4": 36, "target_i": 32, "taxonomi": 41, "termin": [42, 43, 45, 46, 47], "th": 48, "than": 4, "thank": 3, "thei": [45, 47, 48], "them": [3, 4, 5, 42, 43], "therefor": 11, "thi": [1, 4, 39, 42, 43, 44, 45, 46, 47, 48], "those": 10, "thought": 45, "three": [12, 45], "threshold": 38, "thrill": 45, "through": 46, "thu": 45, "ti": 46, "time": [1, 4, 5, 6, 7, 8, 12, 13, 14, 15, 16, 27, 28, 29, 30, 31, 33, 47, 48], "time_limit": 38, "time_penalti": [4, 5, 12], "timemov": 5, "timespe": 5, "timondesch": 45, "tip": 32, "titl": [2, 39, 42], "tomekst": 45, "tool": 45, "toolkit": [39, 41, 42], "top": [27, 28, 29, 30, 31], "torqu": 32, "touch": 48, "track": [47, 48], "trade": 45, "train": 48, "transfer": [3, 10], "transform": 45, "travel": 10, "treasur": [3, 4, 12, 37, 47, 48], "tree": [3, 12, 38], "triangl": 10, "true": [4, 6, 7, 8, 13, 14, 15, 38, 47], "truncat": [38, 42, 43, 45, 46, 47], "tuto": 45, "tutori": 46, "two": [9, 13, 14, 15, 16, 32, 33, 38, 48], "txt": 1, "type": [12, 13, 14, 15, 16, 45], "u": 3, "unbreakable_bottl": 4, "unbreakablebottl": 4, "under": [40, 45], "underwat": [6, 7, 8], "unpin": 45, "until": 38, "unwrap": 45, "up": [4, 6, 7, 8, 10, 37, 38], "upper": [13, 14, 15], "upstream": 38, "us": [6, 7, 8, 13, 14, 15, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48], "usag": 45, "user": 45, "util": [9, 45], "v0": [3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 20, 21, 27, 28, 29, 30, 31, 33, 36, 37, 38, 42, 43, 47, 48], "v2": [5, 45], "v3": [25, 26, 45], "v4": [17, 18, 19, 22, 23, 24, 32, 34, 35, 36, 45], "valu": [4, 6, 7, 8, 11, 12, 41], "vamplew": [5, 12], "variabl": 47, "variou": [3, 40], "vecenv": 45, "vector": [10, 11, 13, 14, 15, 27, 28, 29, 30, 31, 33, 42, 45, 46, 48], "vector_reward": [42, 43, 45], "vectorenv": 47, "vectori": 45, "vehicl": 16, "veloc": [17, 18, 24, 32, 34, 35, 36], "veri": [42, 43, 46], "version": [5, 10, 12, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 45], "via": [41, 47], "vitamin": [11, 12], "wa": [3, 4, 5, 6, 7, 8, 13, 14, 15, 41, 45], "wai": [3, 10], "walker2d": 36, "walker2denv": 35, "wall": 10, "want": 3, "warn": [16, 45], "water": [3, 11, 12, 16, 45], "we": [3, 42, 45, 46], "websit": [42, 45], "weight": [17, 18, 19, 22, 23, 34, 42, 43, 45, 48], "welfar": 41, "well": [42, 45, 46], "were": 10, "when": [4, 6, 7, 8, 9, 10, 11, 13, 14, 15, 33, 37, 45, 46], "where": [6, 7, 8, 9, 11, 27, 28, 29, 30, 31, 45], "whether": [13, 14, 15, 38], "which": [4, 5, 6, 7, 8, 9, 10, 42, 45, 46, 47, 48], "while": [4, 10, 12, 16], "within": [45, 46, 47], "wood": [9, 12], "wood_amount": 12, "woodproba": 9, "work": [42, 47], "worker": 45, "workshop": [2, 41], "world": [6, 7, 8], "would": 3, "wrap": [45, 47], "wrapped_env": 47, "wrapper": [40, 42, 43, 45], "wrt": 38, "x": [6, 7, 8, 17, 18, 22, 23, 24, 33, 34, 35, 37], "x_po": 16, "x_veloc": [36, 45], "xu": 36, "y": [6, 7, 8, 17, 18, 37], "y_veloc": 36, "yang": [6, 7, 8, 11, 12, 16], "year": [2, 39, 42], "you": [3, 39, 42, 43, 44, 45, 46], "your": [1, 39, 42], "your_ag": [42, 43, 45], "z": [22, 23], "zero": [32, 45]}, "titles": ["404 - Page Not Found", "MO-Gymnasium documentation", "<no title>", "Community", "Breakable-Bottles", "Classic Control", "Deep-Sea-Treasure", "Deep-Sea-Treasure-Concave", "Deep-Sea-Treasure-Mirrored", "Fishwood", "Four-Room", "Fruit-Tree", "Grid-World", "Minecart", "Minecart-Deterministic", "Minecart-Rgb", "Miscellaneous", "MO-Ant", "MO-Ant-2D", "MO-Halfcheetah", "MO-Highway", "MO-Highway-Fast", "MO-Hopper", "MO-Hopper-2D", "MO-Humanoid", "MO-Lunar-Lander", "MO-Lunar-Lander-Continuous", "MO-Mountaincar", "MO-Mountaincar-3D", "MO-Mountaincar-Timemove", "MO-Mountaincar-Timespeed", "MO-Mountaincarcontinuous", "MO-Reacher", "MO-Supermario", "MO-Swimmer", "MO-Walker2D", "MuJoCo", "Resource-Gathering", "Water-Reservoir", "Citation", "MORL Baselines", "List of Publications", "API", "API", "Install", "Release Notes", "Creating a custom environment", "Vector Wrappers", "Wrappers"], "titleterms": {"0": 45, "1": [45, 46], "2": [45, 46], "29": 45, "2d": [18, 23], "3": [45, 46], "3d": 28, "4": [45, 46], "404": 0, "Not": 0, "The": 0, "acknowledg": 3, "action": [4, 6, 7, 8, 9, 10, 11, 13, 14, 15, 32, 37, 38], "ant": [17, 18], "api": [42, 43], "argument": [4, 6, 7, 8, 9, 10, 13, 14, 15, 38], "baselin": 40, "becom": 45, "better": 45, "bottl": [4, 45], "breakabl": [4, 45], "bug": 45, "build": 1, "citat": 39, "cite": 42, "class": 46, "classic": 5, "commun": 3, "concav": 7, "continu": 26, "control": 5, "could": 0, "creat": 46, "credit": [4, 6, 7, 8, 9, 10, 13, 14, 15, 37, 38], "custom": 46, "deep": [6, 7, 8, 45], "descript": [4, 6, 7, 8, 9, 10, 11, 13, 14, 15, 17, 18, 19, 20, 22, 23, 24, 25, 26, 32, 33, 34, 35, 37, 38], "determinist": 14, "document": [1, 45], "environ": [45, 46], "episod": [4, 6, 7, 8, 10, 11, 13, 14, 15, 33, 37], "evalu": 45, "fast": 21, "fishwood": 9, "fix": 45, "found": 0, "four": 10, "front": 45, "fruit": [11, 45], "gather": 37, "grid": 12, "gymnasium": [1, 45], "halfcheetah": 19, "highwai": [20, 21], "hopper": [22, 23], "humanoid": 24, "improv": 45, "instal": [42, 44], "instanti": 46, "known": 45, "lander": [25, 26], "linearreward": 48, "list": 41, "lunar": [25, 26], "matur": 45, "migrat": 45, "minecart": [13, 14, 15], "mirror": [8, 45], "miscellan": 16, "mo": [1, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 45], "moclipreward": 48, "momaxandskipobserv": 48, "monormalizereward": 48, "more": 45, "morecordepisodestatist": [47, 48], "morl": 40, "mosyncvectorenv": 47, "mountaincar": [27, 28, 29, 30, 45], "mountaincarcontinu": 31, "mujoco": [36, 45], "new": [45, 46], "note": 45, "observ": [4, 6, 7, 8, 9, 10, 11, 13, 14, 15, 32, 37, 38], "page": [0, 45], "pareto": 45, "polici": 45, "public": 41, "pygam": 45, "reacher": [32, 45], "refer": 10, "regist": 46, "releas": 45, "render": 45, "request": 0, "reservoir": 38, "resourc": 37, "reward": [4, 6, 7, 8, 9, 10, 11, 13, 14, 15, 17, 18, 19, 20, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 37, 38], "rgb": 15, "room": 10, "sea": [6, 7, 8, 45], "space": [4, 6, 7, 8, 9, 10, 11, 13, 14, 15, 17, 18, 19, 20, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 37, 38], "start": [4, 6, 7, 8, 9, 10, 11, 13, 14, 15, 37, 38], "state": [4, 6, 7, 8, 9, 10, 11, 13, 14, 15, 37, 38], "supermario": 33, "support": 45, "swimmer": 34, "termin": [4, 6, 7, 8, 9, 10, 11, 13, 14, 15, 33, 37], "test": [45, 46], "timemov": 29, "timespe": 30, "treasur": [6, 7, 8, 45], "tree": [11, 45], "updat": 45, "v0": 45, "v1": 45, "vector": 47, "walker2d": 35, "water": 38, "webpag": 45, "world": 12, "wrapper": [47, 48], "your": 46}}) \ No newline at end of file diff --git a/tutorials/custom_env/index.html b/tutorials/custom_env/index.html index d06175b0..5e0ae121 100644 --- a/tutorials/custom_env/index.html +++ b/tutorials/custom_env/index.html @@ -11,7 +11,7 @@ - + Creating a custom environment - MO-Gymnasium Documentation @@ -215,6 +215,7 @@
  • Install
  • API
  • Wrappers
    • +
  • Vector Wrappers
  • MORL Baselines

    • Environments

    @@ -234,11 +235,14 @@
  • MO-Mountaincar
  • MO-Mountaincarcontinuous
  • MO-Lunar-Lander
    • +
  • MO-Lunar-Lander-Continuous
  • Miscellaneous @@ -327,10 +331,10 @@
    -

    Creating a custom environment#

    +

    Creating a custom environment

    This tutorials goes through the steps of creating a custom environment for MO-Gymnasium. Since MO-Gymnasium is closely tied to Gymnasium, we will refer to its documentation for some parts.

    -

    1. Create a new environment class#

    +

    1. Create a new environment class

    Create an environment class that inherits from gymnasium.Env. The class must implement the following methods:

    • __init__(self, ...) - The constructor of the class. It should initialize the environment and set the self.action_space andself.observation_space attributes as in classical Gymnasium (see Spaces. Moreover, since we are dealing with multiple objective/rewards, you should define a self.reward_space attribute that defines the shape of the vector rewards returned by the environment, as well as self.reward_dim which is an integer defining the size of the reward vector.

      • @@ -341,7 +345,7 @@

      1. Create a new environment class -

      2. Register the environment#

      +

      2. Register the environment

      Register the environment in the registry. This is done by adding the following line to the __init__.py file in your env directory:

      from gymnasium.envs.registration import register
 register(
@@ -352,11 +356,11 @@ 
      2. Register the environment
-
      3. Test the environment#
      
+
      3. Test the environment
      
 
      If your environment is registered within the MO-Gymnasium repository (step 2), it should be automatically pulled for testing when you run pytest.
    -

    4. Instantiate your environment#

    +

    4. Instantiate your environment

    See our API documentation, but essentially:

    import mo_gymnasium
 env = mo_gymnasium.make('my_env_v0')
@@ -461,8 +465,8 @@ 
    4. Instantiate your environment
-    
+    
+    
     
     
     
diff --git a/wrappers/vector_wrappers/index.html b/wrappers/vector_wrappers/index.html
new file mode 100644
index 00000000..d0fee156
--- /dev/null
+++ b/wrappers/vector_wrappers/index.html
@@ -0,0 +1,713 @@
+
+
+  
+    
+    
+    
+    
+    
+    
+    
+
+        
+
+    
+        Vector Wrappers - MO-Gymnasium Documentation
+      
+    
+    
+    
+    
+
+
+
+  
+    
    
+      
    
+        
    
+          
+        
    
+        
    
+          
+              
+              
+            MO-Gymnasium Documentation
+          
+        
    
+        
    
+          
    
+            
+            
+          
    
+        
    
+      
    
+    
    
+
+    
+    
+    
+
+
+  
+    Contents
+    
+      
+    
+  
+  
+    Menu
+    
+      
+      
+      
+    
+  
+  
+    Expand
+    
+      
+    
+  
+  
+    Light mode
+    
+      
+      
+      
+      
+      
+      
+      
+      
+      
+    
+  
+  
+    Dark mode
+    
+      
+      
+    
+  
+  
+    Auto light/dark mode
+    
+      
+      
+      
+      
+      
+      
+      
+    
+  
+
+
+
+
+
+
+
+
    
+  
+  
+  
    
+
+    
+
+    
+
+    
    
+      
    
+        
    
+          
+            
+              
+            
+            Back to top
+          
+          
    
+  
+    
+    
+  
+
    
+              
+            
    
+            
+          
    
+          
    
+            
+            
    
+
    Vector Wrappers
    
+
    Similar to the normal wrappers, MO-Gymnasium provides a few wrappers that are specifically designed to work with vectorized environments. They are all available directly from the mo_gymnasium.wrappers.vector module.
    
+
    
+
    MOSyncVectorEnv
    
+
    
+
    
+class mo_gymnasium.wrappers.vector.MOSyncVectorEnv(env_fns: Iterator[callable], copy: bool = True)
    
+
    Vectorized environment that serially runs multiple environments.
    
+
    Example
    
+
    >>> import mo_gymnasium as mo_gym
+
    
+
    
+
    >>> envs = mo_gym.wrappers.vector.MOSyncVectorEnv([
+...     lambda: mo_gym.make("deep-sea-treasure-v0") for _ in range(4)
+... ])
+>>> envs
+MOSyncVectorEnv(num_envs=4)
+>>> obs, infos = envs.reset()
+>>> obs
+array([[0, 0], [0, 0], [0, 0], [0, 0]], dtype=int32)
+>>> _ = envs.action_space.seed(42)
+>>> actions = envs.action_space.sample()
+>>> obs, rewards, terminateds, truncateds, infos = envs.step([0, 1, 2, 3])
+>>> obs
+array([[0, 0], [1, 0], [0, 0], [0, 3]], dtype=int32)
+>>> rewards
+array([[0., -1.], [0.7, -1.], [0., -1.], [0., -1.]], dtype=float32)
+>>> terminateds
+array([False,  True, False, False])
+
    
+
    
+
    
+
+
    
+
    
+
    MORecordEpisodeStatistics
    
+
    
+
    
+class mo_gymnasium.wrappers.vector.MORecordEpisodeStatistics(env: VectorEnv, gamma: float = 1.0, buffer_length: int = 100, stats_key: str = 'episode')
    
+
    This wrapper will keep track of cumulative rewards and episode lengths.
    
+
    At the end of any episode within the vectorized env, the statistics of the episode
+will be added to info using the key episode, and the _episode key
+is used to indicate the environment index which has a terminated or truncated episode.
    
+
    
+
    For a vectorized environments the output will be in the form of (be careful to first wrap the env into vector before applying MORewordStatistics):
    
+
    >>> infos = { 
+...     "episode": {
+...         "r": "<array of cumulative reward for each done sub-environment (2d array, shape (num_envs, dim_reward))>",
+...         "dr": "<array of discounted reward for each done sub-environment (2d array, shape (num_envs, dim_reward))>",
+...         "l": "<array of episode length for each done sub-environment (array)>",
+...         "t": "<array of elapsed time since beginning of episode for each done sub-environment (array)>"
+...     },
+...     "_episode": "<boolean array of length num-envs>"
+... }
+
    
+
    
+
    
+
    Moreover, the most recent rewards and episode lengths are stored in buffers that can be accessed via
+wrapped_env.return_queue and wrapped_env.length_queue respectively.
    
+
    
+
    Variables:
    
+
      
+
    • return_queue – The cumulative rewards of the last deque_size-many episodes
      • 
+
    • length_queue – The lengths of the last deque_size-many episodes
      • 
+
    
+
    
+
    
+
    
+
+
    
+
    
+
+          
    
+        
    
+        
+      
    
+      
+    
    
+  
    
+
    
+    
+
+    
+    
+
+    
+    
+    
+    
+    
+    
+
+    
+    
+
+    
+
\ No newline at end of file
diff --git a/wrappers/wrappers/index.html b/wrappers/wrappers/index.html
index a73dbd8c..22a8655f 100644
--- a/wrappers/wrappers/index.html
+++ b/wrappers/wrappers/index.html
@@ -8,10 +8,10 @@
     
     
     
-
+
         
 
-    
+    
         Wrappers - MO-Gymnasium Documentation
       
     
@@ -215,6 +215,7 @@
 
  • Install
    • 
 
  • API
    • 
 
  • Wrappers
    • 
+
  • Vector Wrappers
    • 
 
  • MORL Baselines
    • 
 
 
    Environments
    
@@ -234,11 +235,14 @@
 
  • MO-Mountaincar
    • 
 
  • MO-Mountaincarcontinuous
    • 
 
  • MO-Lunar-Lander
    • 
+
  • MO-Lunar-Lander-Continuous
    •
  • Miscellaneous @@ -326,77 +330,73 @@
    -

    Wrappers#

    -

    A few wrappers inspired from Gymnasium’s wrappers are available in MO-Gymnasium. They are all available directly from the mo_gymnasium module.

    +

    Wrappers

    +

    A few wrappers inspired from Gymnasium’s wrappers are available in MO-Gymnasium. They are all available directly from the mo_gymnasium.wrappers module.

    -

    LinearReward#

    +

    LinearReward

    -
    -class mo_gymnasium.LinearReward(env: Env, weight: ndarray | None = None)#
    +
    +class mo_gymnasium.wrappers.LinearReward(env: Env, weight: ndarray | None = None)

    Makes the env return a scalar reward, which is the dot-product between the reward vector and the weight vector.

    -

    MONormalizeReward#

    +

    MONormalizeReward

    -
    -class mo_gymnasium.MONormalizeReward(env: Env, idx: int, gamma: float = 0.99, epsilon: float = 1e-08)#
    +
    +class mo_gymnasium.wrappers.MONormalizeReward(env: Env, idx: int, gamma: float = 0.99, epsilon: float = 1e-08)

    Wrapper to normalize the reward component at index idx. Does not touch other reward components.

    +

    This code is heavily inspired on Gymnasium’s except that it extracts the reward component at given idx, normalizes it, and reinjects it.

    +

    (!) This smoothes the moving average of the reward, which can be useful for training stability. But it does not “normalize” the reward in the sense of making it have a mean of 0 and a standard deviation of 1.

    +

    Example

    +
    >>> import mo_gymnasium as mo_gym
+>>> from mo_gymnasium.wrappers import MONormalizeReward
+>>> env = mo_gym.make("deep-sea-treasure-v0")
+>>> norm_treasure_env = MONormalizeReward(env, idx=0)
+>>> both_norm_env = MONormalizeReward(norm_treasure_env, idx=1)
+>>> both_norm_env.reset() # This one normalizes both rewards
+
    +
    -

    MOClipReward#

    +

    MOClipReward

    -
    -class mo_gymnasium.MOClipReward(env: Env, idx: int, min_r, max_r)#
    +
    +class mo_gymnasium.wrappers.MOClipReward(env: Env, idx: int, min_r, max_r)

    Clip reward[idx] to [min, max].

    -
    -
    -

    MOSyncVectorEnv#

    -
    -
    -class mo_gymnasium.MOSyncVectorEnv(env_fns: Iterator[callable], copy: bool = True)#
    -

    Vectorized environment that serially runs multiple environments.

    -
    -
    -

    MORecordEpisodeStatistics#

    +

    MORecordEpisodeStatistics

    -
    -class mo_gymnasium.MORecordEpisodeStatistics(env: Env, gamma: float = 1.0, deque_size: int = 100)#
    +
    +class mo_gymnasium.wrappers.MORecordEpisodeStatistics(env: Env, gamma: float = 1.0, buffer_length: int = 100, stats_key: str = 'episode')

    This wrapper will keep track of cumulative rewards and episode lengths.

    After the completion of an episode, info will look like this:

    >>> info = {
 ...     "episode": {
 ...         "r": "<cumulative reward (array)>",
 ...         "dr": "<discounted reward (array)>",
-...         "l": "<episode length (scalar)>", # contrary to Gymnasium, these are not a numpy array
+...         "l": "<episode length (scalar)>",
 ...         "t": "<elapsed time since beginning of episode (scalar)>"
 ...     },
 ... }
    -

    For a vectorized environments the output will be in the form of (be careful to first wrap the env into vector before applying MORewordStatistics):

    -
    >>> infos = {
-...     "final_observation": "<array of length num-envs>",
-...     "_final_observation": "<boolean array of length num-envs>",
-...     "final_info": "<array of length num-envs>",
-...     "_final_info": "<boolean array of length num-envs>",
-...     "episode": {
-...         "r": "<array of cumulative reward (2d array, shape (num_envs, dim_reward))>",
-...         "dr": "<array of discounted reward (2d array, shape (num_envs, dim_reward))>",
-...         "l": "<array of episode length (array)>",
-...         "t": "<array of elapsed time since beginning of episode (array)>"
-...     },
-...     "_episode": "<boolean array of length num-envs>"
-... }
-
    -
    +
    + +
    +
    +

    MOMaxAndSkipObservation

    +
    +
    +class mo_gymnasium.wrappers.MOMaxAndSkipObservation(env: Env[ObsType, ActType], skip: int = 4)
    +

    This wrapper will return only every skip-th frame (frameskipping) and return the max between the two last observations.

    +

    Note: This wrapper is based on the wrapper from stable-baselines3: https://stable-baselines3.readthedocs.io/en/master/_modules/stable_baselines3/common/atari_wrappers.html#MaxAndSkipEnv

    @@ -407,12 +407,12 @@

    MORecordEpisode