Deploying to gh-pages from @ 7e2062d 🚀

main/.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: 6e61249047292981a84104a53735e4b9
+config: 77df1ca8f1dadbd38f8151723b35a772
 tags: d77d1c0d9ca2f4c8421862c7c5a0d620

main/_downloads/d1980709c80836b9d7e8f9131878afbb/blackjack_tutorial.ipynb

@@ -140,7 +140,7 @@
       },
       "outputs": [],
       "source": [
-        "env = gym.wrappers.RecordEpisodeStatistics(env, buffer_length=n_episodes)\nfor episode in tqdm(range(n_episodes)):\n    obs, info = env.reset()\n    done = False\n\n    # play one episode\n    while not done:\n        action = agent.get_action(env, obs)\n        next_obs, reward, terminated, truncated, info = env.step(action)\n\n        # update the agent\n        agent.update(obs, action, reward, terminated, next_obs)\n\n        # update if the environment is done and the current obs\n        done = terminated or truncated\n        obs = next_obs\n\n    agent.decay_epsilon()"
+        "env = gym.wrappers.RecordEpisodeStatistics(env, deque_size=n_episodes)\nfor episode in tqdm(range(n_episodes)):\n    obs, info = env.reset()\n    done = False\n\n    # play one episode\n    while not done:\n        action = agent.get_action(env, obs)\n        next_obs, reward, terminated, truncated, info = env.step(action)\n\n        # update the agent\n        agent.update(obs, action, reward, terminated, next_obs)\n\n        # update if the environment is done and the current obs\n        done = terminated or truncated\n        obs = next_obs\n\n    agent.decay_epsilon()"
       ]
     },
     {

main/_downloads/e1249c888e952c938d27855c3210a4bb/blackjack_tutorial.py

@@ -275,7 +275,7 @@ def decay_epsilon(self):
 #
 
 
-env = gym.wrappers.RecordEpisodeStatistics(env, buffer_length=n_episodes)
+env = gym.wrappers.RecordEpisodeStatistics(env, deque_size=n_episodes)
 for episode in tqdm(range(n_episodes)):
     obs, info = env.reset()
     done = False

main/tutorials/training_agents/blackjack_tutorial/index.html

@@ -605,7 +605,7 @@ <h2>Building an agent<a class="headerlink" href="#building-an-agent" title="Link
 <p>Info: The current hyperparameters are set to quickly train a decent agent.
 If you want to converge to the optimal policy, try increasing
 the n_episodes by 10x and lower the learning_rate (e.g. to 0.001).</p>
-<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">env</span> <span class="o">=</span> <span class="n">gym</span><span class="o">.</span><span class="n">wrappers</span><span class="o">.</span><span class="n">RecordEpisodeStatistics</span><span class="p">(</span><span class="n">env</span><span class="p">,</span> <span class="n">buffer_length</span><span class="o">=</span><span class="n">n_episodes</span><span class="p">)</span>
+<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">env</span> <span class="o">=</span> <span class="n">gym</span><span class="o">.</span><span class="n">wrappers</span><span class="o">.</span><span class="n">RecordEpisodeStatistics</span><span class="p">(</span><span class="n">env</span><span class="p">,</span> <span class="n">deque_size</span><span class="o">=</span><span class="n">n_episodes</span><span class="p">)</span>
 <span class="k">for</span> <span class="n">episode</span> <span class="ow">in</span> <span class="n">tqdm</span><span class="p">(</span><span class="nb">range</span><span class="p">(</span><span class="n">n_episodes</span><span class="p">)):</span>
     <span class="n">obs</span><span class="p">,</span> <span class="n">info</span> <span class="o">=</span> <span class="n">env</span><span class="o">.</span><span class="n">reset</span><span class="p">()</span>
     <span class="n">done</span> <span class="o">=</span> <span class="kc">False</span>