Merge branch 'master' into agilerl-updates

Farama-Foundation · Dec 4, 2024 · 07a8223 · 07a8223
2 parents 9ae9b6a + 00cb35c
commit 07a8223
Show file tree

Hide file tree

Showing 65 changed files with 1,183 additions and 878 deletions.
diff --git a/.github/workflows/build-publish.yml b/.github/workflows/build-publish.yml
@@ -31,6 +31,9 @@ jobs:
                     - os: ubuntu-latest
                       python: 311
                       platform: manylinux_x86_64
+                    - os: ubuntu-latest
+                      python: 312
+                      platform: manylinux_x86_64
 
         steps:
             - uses: actions/checkout@v4

diff --git a/.github/workflows/linux-test.yml b/.github/workflows/linux-test.yml
@@ -15,7 +15,7 @@ jobs:
         runs-on: ubuntu-latest
         strategy:
             matrix:
-                python-version: ['3.8', '3.9', '3.10', '3.11']
+                python-version: ['3.8', '3.9', '3.10', '3.11', '3.12']
         steps:
             - uses: actions/checkout@v4
             - name: Set up Python ${{ matrix.python-version }}

diff --git a/.github/workflows/linux-tutorials-test.yml b/.github/workflows/linux-tutorials-test.yml
@@ -15,9 +15,11 @@ jobs:
         runs-on: ubuntu-latest
         strategy:
             fail-fast: false
+
             matrix:
                 python-version: ['3.8', '3.9', '3.10', '3.11']
                 tutorial: [Tianshou, CustomEnvironment, CleanRL, SB3/kaz, SB3/waterworld, SB3/connect_four, SB3/test]  # TODO: fix tutorials and add back Ray
+
         steps:
             - uses: actions/checkout@v4
             - name: Set up Python ${{ matrix.python-version }}

diff --git a/.github/workflows/macos-test.yml b/.github/workflows/macos-test.yml
@@ -15,7 +15,7 @@ jobs:
             matrix:
             # Big Sur, Monterey
                 os: [macos-11, macos-12]
-                python-version: ['3.8', '3.9', '3.10', '3.11']
+                python-version: ['3.8', '3.9', '3.10', '3.11', '3.12']
         steps:
             - uses: actions/checkout@v4
             - name: Set up Python ${{ matrix.python-version }}

diff --git a/README.md b/README.md
@@ -73,11 +73,6 @@ SuperSuit is a library that includes all commonly used wrappers in RL (frame sta
 
 PettingZoo keeps strict versioning for reproducibility reasons. All environments end in a suffix like "\_v0".  When changes are made to environments that might impact learning results, the number is increased by one to prevent potential confusion.
 
-## Project Maintainers
-Project Manager: [Elliot Tower](https://github.com/elliottower/)
-
-Maintenance for this project is also contributed by the broader Farama team: [farama.org/team](https://farama.org/team).
-
 ## Citation
 
 To cite this project in publication, please use
@@ -92,3 +87,6 @@ To cite this project in publication, please use
   year={2021}
 }
 ```
+## Project Maintainers
+- Project Manager: [David Gerard](https://github.com/David-GERARD) - `[email protected]`.
+- Maintenance for this project is also contributed by the broader Farama team: [farama.org/team](https://farama.org/team).
diff --git a/docs/api/aec.md b/docs/api/aec.md
@@ -94,8 +94,8 @@ The [_Agent Environment Cycle_](https://arxiv.org/abs/2009.13051) (AEC) model wa
 
 In an AEC environment, agents act sequentially, receiving updated observations and rewards before taking an action. The environment updates after each agent's step, making it a natural way of representing sequential games such as Chess. The AEC model is flexible enough to handle any type of game that multi-agent RL can consider.
 
-with the underlying environment updating after each agent's step. Agents receive updated observations and rewards at the beginning of their . The environment is updated after every step,
-This is a natural way of representing sequential games such as Chess, and
+with the underlying environment updating after each agent's step. Agents receive updated observations and rewards at the beginning of their turn. The environment is updated after every step,
+This is a natural way of representing sequential games such as Chess and Go.
 
 ```{figure} /_static/img/aec_cycle_figure.png
     :width: 480px

diff --git a/docs/api/utils.md b/docs/api/utils.md
@@ -165,7 +165,7 @@ Base class which is used by [CaptureStdoutWrapper](https://pettingzoo.farama.org
 
 The agent selector utility allows for easy cycling of agents in an AEC environment. At any time it can be reset or reinitialized with a new order, allowing for changes in turn order or handling a dynamic number of agents (see [Knights-Archers-Zombies](https://pettingzoo.farama.org/environments/butterfly/knights_archers_zombies/) for an example of spawning/killing agents)
 
-Note: while many PettingZoo environments use agent_selector to manage agent cycling internally, it is not intended to be used externally when interacting with an environment. Instead, use `for agent in env.agent_iter()` (see [AEC API Usage](https://pettingzoo.farama.org/api/aec/#usage)).
+Note: while many PettingZoo environments use AgentSelector to manage agent cycling internally, it is not intended to be used externally when interacting with an environment. Instead, use `for agent in env.agent_iter()` (see [AEC API Usage](https://pettingzoo.farama.org/api/aec/#usage)).
 
 ```{eval-rst}
 .. currentmodule:: pettingzoo.utils

diff --git a/docs/code_examples/aec_rps.py b/docs/code_examples/aec_rps.py
@@ -5,7 +5,7 @@
 from gymnasium.spaces import Discrete
 
 from pettingzoo import AECEnv
-from pettingzoo.utils import agent_selector, wrappers
+from pettingzoo.utils import AgentSelector, wrappers
 
 ROCK = 0
 PAPER = 1
@@ -156,9 +156,9 @@ def reset(self, seed=None, options=None):
         self.observations = {agent: NONE for agent in self.agents}
         self.num_moves = 0
         """
-        Our agent_selector utility allows easy cyclic stepping through the agents list.
+        Our AgentSelector utility allows easy cyclic stepping through the agents list.
         """
-        self._agent_selector = agent_selector(self.agents)
+        self._agent_selector = AgentSelector(self.agents)
         self.agent_selection = self._agent_selector.next()
 
     def step(self, action):

diff --git a/docs/code_examples/aec_rps_usage.py b/docs/code_examples/aec_rps_usage.py
@@ -1,4 +1,4 @@
-import aec_rps
+from . import aec_rps
 
 env = aec_rps.env(render_mode="human")
 env.reset(seed=42)

diff --git a/docs/code_examples/parallel_rps_usage.py b/docs/code_examples/parallel_rps_usage.py
@@ -1,4 +1,4 @@
-import parallel_rps
+from . import parallel_rps
 
 env = parallel_rps.parallel_env(render_mode="human")
 observations, infos = env.reset()

diff --git a/docs/content/environment_creation.md b/docs/content/environment_creation.md
@@ -62,14 +62,14 @@ The utils directory also contain some classes which are only helpful for develop
 
 ### Agent selector
 
-The `agent_selector` class steps through agents in a cycle
+The `AgentSelector` class steps through agents in a cycle
 
 It can be used as follows to cycle through the list of agents:
 
 ```python
-from pettingzoo.utils import agent_selector
+from pettingzoo.utils import AgentSelector
 agents = ["agent_1", "agent_2", "agent_3"]
-selector = agent_selector(agents)
+selector = AgentSelector(agents)
 agent_selection = selector.reset()
 # agent_selection will be "agent_1"
 for i in range(100):

diff --git a/docs/environments/third_party_envs.md b/docs/environments/third_party_envs.md
@@ -12,6 +12,18 @@ lastpage:
 ## Environments using the latest versions of PettingZoo
 *Due to a very recent major release of PettingZoo, there are currently few contributed third-party environments. If you'd like to contribute one, please reach out on [Discord](https://discord.gg/nHg2JRN489).*
 
+### [gfootball-gymnasium-pettingzoo](https://github.com/xihuai18/gfootball-gymnasium-pettingzoo)
+[![PettingZoo version dependency](https://img.shields.io/badge/PettingZoo-v1.24.3-blue)]()
+[![GitHub stars](https://img.shields.io/github/stars/xihuai18/gfootball-gymnasium-pettingzoo)]()
+
+Google Research Football ([GRF](https://github.com/google-research/football)) with Gymnasium and PettingZoo Compatibility.
+
+### [SMAC and SMACv2 with latest PettingZoo APIs](https://github.com/xihuai18/SMAC-PettingZoo)
+[![PettingZoo version dependency](https://img.shields.io/badge/PettingZoo-v1.24.3-blue)]()
+[![GitHub stars](https://img.shields.io/github/stars/xihuai18/gfootball-gymnasium-pettingzoo)]()
+
+[SMAC](https://github.com/oxwhirl/smac) and [SMACv2](https://github.com/oxwhirl/smacv2) with the latest PettingZoo Parallel APIs.
+
 ### [Sumo-RL](https://github.com/LucasAlegre/sumo-rl)
 
 [![PettingZoo version dependency](https://img.shields.io/badge/PettingZoo-v1.22.2-blue)]()
@@ -57,6 +69,12 @@ CookingZoo: a gym-cooking derivative to simulate a complex cooking environment.
 
 A library for doing reinforcement learning using [Crazyflie](https://www.bitcraze.io/products/crazyflie-2-1/) drones.
 
+### [DSSE: Drone Swarm Search Environment](https://github.com/pfeinsper/drone-swarm-search)
+[![PettingZoo version dependency](https://img.shields.io/badge/PettingZoo-v1.22.3-blue)]()
+![GitHub stars](https://img.shields.io/github/stars/pfeinsper/drone-swarm-search)
+
+A single and multi-agent environment to train swarms of drones for maritime search.
+
 
 ### [PettingZoo Dilemma Envs](https://github.com/tianyu-z/pettingzoo_dilemma_envs)