Deploying to gh-pages from @ 4db1fd0 🚀

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: 07dea26af62d7a1122838d0daf622e7d
+config: dfbf63b153c0ca30fc635427bd1b74b1
 tags: d77d1c0d9ca2f4c8421862c7c5a0d620

main/release_notes/index.html

@@ -331,6 +331,11 @@
 
             <section class="tex2jax_ignore mathjax_ignore" id="release-notes">
 <h1>Release Notes<a class="headerlink" href="#release-notes" title="Link to this heading">¶</a></h1>
+<section id="release-v1-3-1">
+<h2>v1.3.1: MO-Gymnasium 1.3.1 Release: Doc fixes<a class="headerlink" href="#release-v1-3-1" title="Link to this heading">¶</a></h2>
+<p><em>Released on 2024-10-28 - <a class="reference external" href="https://github.com/Farama-Foundation/MO-Gymnasium/releases/tag/v1.3.1">GitHub</a> - <a class="reference external" href="https://pypi.org/project/mo-gymnasium/v1.3.1/">PyPI</a></em></p>
+<p>Doc fixes</p>
+<p><strong>Full Changelog</strong>: <a class="commit-link" href="https://github.com/Farama-Foundation/MO-Gymnasium/compare/v1.3.0...v1.3.1"><tt>v1.3.0...v1.3.1</tt></a></p></section>
 <section id="release-v1-3-0">
 <h2>v1.3.0: MO-Gymnasium 1.3.0 Release: New Mujoco v5 Environments<a class="headerlink" href="#release-v1-3-0" title="Link to this heading">¶</a></h2>
 <p><em>Released on 2024-10-28 - <a class="reference external" href="https://github.com/Farama-Foundation/MO-Gymnasium/releases/tag/v1.3.0">GitHub</a> - <a class="reference external" href="https://pypi.org/project/mo-gymnasium/v1.3.0/">PyPI</a></em></p>
@@ -456,12 +461,12 @@ <h1>MO-Gymnasium 1.0.0 Release Notes</h1>
 <p>MORL expands the capabilities of RL to scenarios where agents need to optimize multiple objectives, which may potentially conflict with each other. Each objective is represented by a distinct reward function. In this context, the agent learns to make trade-offs between these objectives based on a reward vector received after each step. For instance, in the well-known Mujoco halfcheetah environment, reward components are combined linearly using predefined weights as shown in the following code snippet from <a href="https://github.com/Farama-Foundation/Gymnasium/blob/main/gymnasium/envs/mujoco/half_cheetah_v4.py#LL201C9-L206C44">Gymnasium</a>:</p>
 <div class="highlight highlight-source-python notranslate position-relative overflow-auto" data-snippet-clipboard-copy-content="ctrl_cost = self.control_cost(action)
 forward_reward = self._forward_reward_weight * x_velocity
-reward = forward_reward - ctrl_cost"><pre><span class="pl-s1">ctrl_cost</span> <span class="pl-c1">=</span> <span class="pl-s1">self</span>.<span class="pl-en">control_cost</span>(<span class="pl-s1">action</span>)
-<span class="pl-s1">forward_reward</span> <span class="pl-c1">=</span> <span class="pl-s1">self</span>.<span class="pl-s1">_forward_reward_weight</span> <span class="pl-c1">*</span> <span class="pl-s1">x_velocity</span>
+reward = forward_reward - ctrl_cost"><pre><span class="pl-s1">ctrl_cost</span> <span class="pl-c1">=</span> <span class="pl-s1">self</span>.<span class="pl-c1">control_cost</span>(<span class="pl-s1">action</span>)
+<span class="pl-s1">forward_reward</span> <span class="pl-c1">=</span> <span class="pl-s1">self</span>.<span class="pl-c1">_forward_reward_weight</span> <span class="pl-c1">*</span> <span class="pl-s1">x_velocity</span>
 <span class="pl-s1">reward</span> <span class="pl-c1">=</span> <span class="pl-s1">forward_reward</span> <span class="pl-c1">-</span> <span class="pl-s1">ctrl_cost</span></pre></div>
 <p>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 <a href="https://gymnasium.farama.org/" rel="nofollow">Gymnasium</a> to the multi-objective setting, where the agents receives a vectorial reward.</p>
 <p>For example, here is an illustration of the multiple policies learned by an MORL agent for the <code>mo-halfcheetah</code> domain, balancing between saving battery and speed:</p>
-<a target="_blank" rel="noopener noreferrer" href="https://private-user-images.githubusercontent.com/11799929/245189948-10796cae-6f84-4690-8e17-d23f792c32c2.gif?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.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.V2kUtC7uCzUmeYVE6yfo9mvpFk7VZJAlPGaaZn4ZZoE"><img src="https://private-user-images.githubusercontent.com/11799929/245189948-10796cae-6f84-4690-8e17-d23f792c32c2.gif?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.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.V2kUtC7uCzUmeYVE6yfo9mvpFk7VZJAlPGaaZn4ZZoE" width="400" content-type-secured-asset="image/gif" style="max-width: 100%;"></a> 
+<a target="_blank" rel="noopener noreferrer" href="https://private-user-images.githubusercontent.com/11799929/245189948-10796cae-6f84-4690-8e17-d23f792c32c2.gif?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.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.F2fS68GJlzcq9t4_2iY0q43p-EUp28QLxTKkiuYHYvY"><img src="https://private-user-images.githubusercontent.com/11799929/245189948-10796cae-6f84-4690-8e17-d23f792c32c2.gif?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.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.F2fS68GJlzcq9t4_2iY0q43p-EUp28QLxTKkiuYHYvY" width="400" content-type-secured-asset="image/gif" style="max-width: 100%;"></a> 
 <p>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.</p>
 <h2>API</h2>
 <div class="highlight highlight-source-python notranslate position-relative overflow-auto" data-snippet-clipboard-copy-content="import gymnasium as gym
@@ -482,15 +487,15 @@ <h2>API</h2>
 <span class="pl-k">import</span> <span class="pl-s1">numpy</span> <span class="pl-k">as</span> <span class="pl-s1">np</span>
 
 <span class="pl-c"># It follows the original Gymnasium API ...</span>
-<span class="pl-s1">env</span> <span class="pl-c1">=</span> <span class="pl-s1">mo_gym</span>.<span class="pl-en">make</span>(<span class="pl-s">'minecart-v0'</span>)
+<span class="pl-s1">env</span> <span class="pl-c1">=</span> <span class="pl-s1">mo_gym</span>.<span class="pl-c1">make</span>(<span class="pl-s">'minecart-v0'</span>)
 
-<span class="pl-s1">obs</span>, <span class="pl-s1">info</span> <span class="pl-c1">=</span> <span class="pl-s1">env</span>.<span class="pl-en">reset</span>()
+<span class="pl-s1">obs</span>, <span class="pl-s1">info</span> <span class="pl-c1">=</span> <span class="pl-s1">env</span>.<span class="pl-c1">reset</span>()
 <span class="pl-c"># but vector_reward is a numpy array!</span>
-<span class="pl-s1">next_obs</span>, <span class="pl-s1">vector_reward</span>, <span class="pl-s1">terminated</span>, <span class="pl-s1">truncated</span>, <span class="pl-s1">info</span> <span class="pl-c1">=</span> <span class="pl-s1">env</span>.<span class="pl-en">step</span>(<span class="pl-s1">your_agent</span>.<span class="pl-en">act</span>(<span class="pl-s1">obs</span>))
+<span class="pl-s1">next_obs</span>, <span class="pl-s1">vector_reward</span>, <span class="pl-s1">terminated</span>, <span class="pl-s1">truncated</span>, <span class="pl-s1">info</span> <span class="pl-c1">=</span> <span class="pl-s1">env</span>.<span class="pl-c1">step</span>(<span class="pl-s1">your_agent</span>.<span class="pl-c1">act</span>(<span class="pl-s1">obs</span>))
 
 <span class="pl-c"># Optionally, you can scalarize the reward function with the LinearReward wrapper.</span>
 <span class="pl-c"># This allows to fall back to single objective RL</span>
-<span class="pl-s1">env</span> <span class="pl-c1">=</span> <span class="pl-s1">mo_gym</span>.<span class="pl-v">LinearReward</span>(<span class="pl-s1">env</span>, <span class="pl-s1">weight</span><span class="pl-c1">=</span><span class="pl-s1">np</span>.<span class="pl-en">array</span>([<span class="pl-c1">0.8</span>, <span class="pl-c1">0.2</span>, <span class="pl-c1">0.2</span>]))</pre></div>
+<span class="pl-s1">env</span> <span class="pl-c1">=</span> <span class="pl-s1">mo_gym</span>.<span class="pl-c1">LinearReward</span>(<span class="pl-s1">env</span>, <span class="pl-s1">weight</span><span class="pl-c1">=</span><span class="pl-s1">np</span>.<span class="pl-c1">array</span>([<span class="pl-c1">0.8</span>, <span class="pl-c1">0.2</span>, <span class="pl-c1">0.2</span>]))</pre></div>
 <h2>Environments</h2>
 <p>We support environments ranging from MORL literature to inherently multi-objective problems in the RL literature such as Mujoco. An exhaustive list of environments is available on our <a href="https://mo-gymnasium.farama.org/environments/all-environments/" rel="nofollow">documentation website</a>.</p>
 <h2>Wrappers</h2>
@@ -685,6 +690,7 @@ <h2>0.1.1<a class="headerlink" href="#release-0-1-1" title="Link to this heading
             <div class="toc-tree">
               <ul>
 <li><a class="reference internal" href="#">Release Notes</a><ul>
+<li><a class="reference internal" href="#release-v1-3-1">v1.3.1: MO-Gymnasium 1.3.1 Release: Doc fixes</a></li>
 <li><a class="reference internal" href="#release-v1-3-0">v1.3.0: MO-Gymnasium 1.3.0 Release: New Mujoco v5 Environments</a></li>
 <li><a class="reference internal" href="#release-v1-2-0">v1.2.0: MO-Gymnasium 1.2.0 Release: Update Gymnasium to v1.0.0, New Mountaincar Environments, Documentation and Test Improvements, and more</a></li>
 <li><a class="reference internal" href="#release-v1-1-0">v1.1.0: MO-Gymnasium 1.1.0 Release: New MuJoCo environments, Mirrored Deep Sea Treasure, Fruit Tree rendering, and more</a></li>