dodox/fancy_gym
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity
better_versioning
fancy_gym/docs/build/html/examples/replanning_envs.html

210 lines
19 KiB
HTML
Raw Permalink Blame History

<!DOCTYPE html>
<html class="writer-html5" lang="en" >
<head>
<meta charset="utf-8" /><meta name="generator" content="Docutils 0.19: https://docutils.sourceforge.io/" />
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
<title>Replanning Example &mdash; Fancy Gym 0.2 documentation</title>
<link rel="stylesheet" href="../_static/pygments.css" type="text/css" />
<link rel="stylesheet" href="../_static/css/theme.css" type="text/css" />
<link rel="stylesheet" href="../_static/style.css" type="text/css" />
<link rel="shortcut icon" href="../_static/icon.svg"/>
<!--[if lt IE 9]>
<script src="../_static/js/html5shiv.min.js"></script>
<![endif]-->
<script data-url_root="../" id="documentation_options" src="../_static/documentation_options.js"></script>
<script src="../_static/jquery.js"></script>
<script src="../_static/underscore.js"></script>
<script src="../_static/_sphinx_javascript_frameworks_compat.js"></script>
<script src="../_static/doctools.js"></script>
<script src="../_static/sphinx_highlight.js"></script>
<script src="../_static/js/theme.js"></script>
<link rel="index" title="Index" href="../genindex.html" />
<link rel="search" title="Search" href="../search.html" />
<link rel="next" title="API" href="../api.html" />
<link rel="prev" title="PD Control Gain Tuning Example" href="pd_control_gain_tuning.html" />
</head>
<body class="wy-body-for-nav">
<div class="wy-grid-for-nav">
<nav data-toggle="wy-nav-shift" class="wy-nav-side">
<div class="wy-side-scroll">
<div class="wy-side-nav-search" >
<a href="../index.html" class="icon icon-home">
Fancy Gym
<img src="../_static/icon.svg" class="logo" alt="Logo"/>
</a>
<div class="version">
0.2
</div>
<div role="search">
<form id="rtd-search-form" class="wy-form" action="../search.html" method="get">
<input type="text" name="q" placeholder="Search docs" aria-label="Search docs" />
<input type="hidden" name="check_keywords" value="yes" />
<input type="hidden" name="area" value="default" />
</form>
</div>
</div><div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="Navigation menu">
<p class="caption" role="heading"><span class="caption-text">User Guide</span></p>
<ul>
<li class="toctree-l1"><a class="reference internal" href="../guide/installation.html">Installation</a></li>
<li class="toctree-l1"><a class="reference internal" href="../guide/episodic_rl.html">What is Episodic RL?</a></li>
<li class="toctree-l1"><a class="reference internal" href="../guide/basic_usage.html">Basic Usage</a></li>
<li class="toctree-l1"><a class="reference internal" href="../guide/upgrading_envs.html">Creating new MP Environments</a></li>
</ul>
<p class="caption" role="heading"><span class="caption-text">Environments</span></p>
<ul>
<li class="toctree-l1"><a class="reference internal" href="../envs/fancy/index.html">Fancy</a></li>
<li class="toctree-l1"><a class="reference internal" href="../envs/dmc.html">DeepMind Control (DMC)</a></li>
<li class="toctree-l1"><a class="reference internal" href="../envs/meta.html">Metaworld</a></li>
<li class="toctree-l1"><a class="reference internal" href="../envs/open_ai.html">Gymnasium</a></li>
</ul>
<p class="caption" role="heading"><span class="caption-text">Examples</span></p>
<ul class="current">
<li class="toctree-l1"><a class="reference internal" href="general.html">General Usage Examples</a></li>
<li class="toctree-l1"><a class="reference internal" href="dmc.html">DeepMind Control Examples</a></li>
<li class="toctree-l1"><a class="reference internal" href="metaworld.html">Metaworld Examples</a></li>
<li class="toctree-l1"><a class="reference internal" href="open_ai.html">OpenAI Envs Examples</a></li>
<li class="toctree-l1"><a class="reference internal" href="movement_primitives.html">Movement Primitives Examples</a></li>
<li class="toctree-l1"><a class="reference internal" href="mp_params_tuning.html">MP Params Tuning Example</a></li>
<li class="toctree-l1"><a class="reference internal" href="pd_control_gain_tuning.html">PD Control Gain Tuning Example</a></li>
<li class="toctree-l1 current"><a class="current reference internal" href="#">Replanning Example</a></li>
</ul>
<p class="caption" role="heading"><span class="caption-text">API</span></p>
<ul>
<li class="toctree-l1"><a class="reference internal" href="../api.html">API</a></li>
</ul>
</div>
</div>
</nav>
<section data-toggle="wy-nav-shift" class="wy-nav-content-wrap"><nav class="wy-nav-top" aria-label="Mobile navigation menu" >
<i data-toggle="wy-nav-top" class="fa fa-bars"></i>
<a href="../index.html">Fancy Gym</a>
</nav>
<div class="wy-nav-content">
<div class="rst-content">
<div role="navigation" aria-label="Page navigation">
<ul class="wy-breadcrumbs">
<li><a href="../index.html" class="icon icon-home" aria-label="Home"></a></li>
<li class="breadcrumb-item active">Replanning Example</li>
<li class="wy-breadcrumbs-aside">
<a href="https://github.com/ALRhub/fancy_gym/blob/release/docs/source/examples/replanning_envs.rst" class="fa fa-github"> Edit on GitHub</a>
</li>
</ul>
<hr/>
</div>
<div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article">
<div itemprop="articleBody">
<section id="replanning-example">
<h1>Replanning Example<a class="headerlink" href="#replanning-example" title="Permalink to this heading"></a></h1>
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="linenos"> 1</span><span class="kn">import</span> <span class="nn">gymnasium</span> <span class="k">as</span> <span class="nn">gym</span>
<span class="linenos"> 2</span><span class="kn">import</span> <span class="nn">fancy_gym</span>
<span class="linenos"> 3</span>
<span class="linenos"> 4</span>
<span class="linenos"> 5</span><span class="k">def</span> <span class="nf">example_run_replanning_env</span><span class="p">(</span><span class="n">env_name</span><span class="o">=</span><span class="s2">&quot;fancy_ProDMP/BoxPushingDenseReplan-v0&quot;</span><span class="p">,</span> <span class="n">seed</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span> <span class="n">iterations</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span> <span class="n">render</span><span class="o">=</span><span class="kc">False</span><span class="p">):</span>
<span class="linenos"> 6</span> <span class="n">env</span> <span class="o">=</span> <span class="n">gym</span><span class="o">.</span><span class="n">make</span><span class="p">(</span><span class="n">env_name</span><span class="p">)</span>
<span class="linenos"> 7</span> <span class="n">env</span><span class="o">.</span><span class="n">reset</span><span class="p">(</span><span class="n">seed</span><span class="o">=</span><span class="n">seed</span><span class="p">)</span>
<span class="linenos"> 8</span> <span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="n">iterations</span><span class="p">):</span>
<span class="linenos"> 9</span> <span class="n">done</span> <span class="o">=</span> <span class="kc">False</span>
<span class="linenos">10</span> <span class="k">while</span> <span class="n">done</span> <span class="ow">is</span> <span class="kc">False</span><span class="p">:</span>
<span class="linenos">11</span> <span class="n">ac</span> <span class="o">=</span> <span class="n">env</span><span class="o">.</span><span class="n">action_space</span><span class="o">.</span><span class="n">sample</span><span class="p">()</span>
<span class="linenos">12</span> <span class="n">obs</span><span class="p">,</span> <span class="n">reward</span><span class="p">,</span> <span class="n">terminated</span><span class="p">,</span> <span class="n">truncated</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">step</span><span class="p">(</span><span class="n">ac</span><span class="p">)</span>
<span class="linenos">13</span> <span class="k">if</span> <span class="n">render</span><span class="p">:</span>
<span class="linenos">14</span> <span class="n">env</span><span class="o">.</span><span class="n">render</span><span class="p">(</span><span class="n">mode</span><span class="o">=</span><span class="s2">&quot;human&quot;</span><span class="p">)</span>
<span class="linenos">15</span> <span class="k">if</span> <span class="n">terminated</span> <span class="ow">or</span> <span class="n">truncated</span><span class="p">:</span>
<span class="linenos">16</span> <span class="n">env</span><span class="o">.</span><span class="n">reset</span><span class="p">()</span>
<span class="linenos">17</span> <span class="n">env</span><span class="o">.</span><span class="n">close</span><span class="p">()</span>
<span class="linenos">18</span> <span class="k">del</span> <span class="n">env</span>
<span class="linenos">19</span>
<span class="linenos">20</span>
<span class="linenos">21</span><span class="k">def</span> <span class="nf">example_custom_replanning_envs</span><span class="p">(</span><span class="n">seed</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="n">iteration</span><span class="o">=</span><span class="mi">100</span><span class="p">,</span> <span class="n">render</span><span class="o">=</span><span class="kc">True</span><span class="p">):</span>
<span class="linenos">22</span> <span class="c1"># id for a step-based environment</span>
<span class="linenos">23</span> <span class="n">base_env_id</span> <span class="o">=</span> <span class="s2">&quot;BoxPushingDense-v0&quot;</span>
<span class="linenos">24</span>
<span class="linenos">25</span> <span class="n">wrappers</span> <span class="o">=</span> <span class="p">[</span><span class="n">fancy_gym</span><span class="o">.</span><span class="n">envs</span><span class="o">.</span><span class="n">mujoco</span><span class="o">.</span><span class="n">box_pushing</span><span class="o">.</span><span class="n">mp_wrapper</span><span class="o">.</span><span class="n">MPWrapper</span><span class="p">]</span>
<span class="linenos">26</span>
<span class="linenos">27</span> <span class="n">trajectory_generator_kwargs</span> <span class="o">=</span> <span class="p">{</span><span class="s1">&#39;trajectory_generator_type&#39;</span><span class="p">:</span> <span class="s1">&#39;prodmp&#39;</span><span class="p">,</span>
<span class="linenos">28</span> <span class="s1">&#39;weights_scale&#39;</span><span class="p">:</span> <span class="mi">1</span><span class="p">}</span>
<span class="linenos">29</span> <span class="n">phase_generator_kwargs</span> <span class="o">=</span> <span class="p">{</span><span class="s1">&#39;phase_generator_type&#39;</span><span class="p">:</span> <span class="s1">&#39;exp&#39;</span><span class="p">}</span>
<span class="linenos">30</span> <span class="n">controller_kwargs</span> <span class="o">=</span> <span class="p">{</span><span class="s1">&#39;controller_type&#39;</span><span class="p">:</span> <span class="s1">&#39;velocity&#39;</span><span class="p">}</span>
<span class="linenos">31</span> <span class="n">basis_generator_kwargs</span> <span class="o">=</span> <span class="p">{</span><span class="s1">&#39;basis_generator_type&#39;</span><span class="p">:</span> <span class="s1">&#39;prodmp&#39;</span><span class="p">,</span>
<span class="linenos">32</span> <span class="s1">&#39;num_basis&#39;</span><span class="p">:</span> <span class="mi">5</span><span class="p">}</span>
<span class="linenos">33</span>
<span class="linenos">34</span> <span class="c1"># max_planning_times: the maximum number of plans can be generated</span>
<span class="linenos">35</span> <span class="c1"># replanning_schedule: the trigger for replanning</span>
<span class="linenos">36</span> <span class="c1"># condition_on_desired: use desired state as the boundary condition for the next plan</span>
<span class="linenos">37</span> <span class="n">black_box_kwargs</span> <span class="o">=</span> <span class="p">{</span><span class="s1">&#39;max_planning_times&#39;</span><span class="p">:</span> <span class="mi">4</span><span class="p">,</span>
<span class="linenos">38</span> <span class="s1">&#39;replanning_schedule&#39;</span><span class="p">:</span> <span class="k">lambda</span> <span class="n">pos</span><span class="p">,</span> <span class="n">vel</span><span class="p">,</span> <span class="n">obs</span><span class="p">,</span> <span class="n">action</span><span class="p">,</span> <span class="n">t</span><span class="p">:</span> <span class="n">t</span> <span class="o">%</span> <span class="mi">25</span> <span class="o">==</span> <span class="mi">0</span><span class="p">,</span>
<span class="linenos">39</span> <span class="s1">&#39;condition_on_desired&#39;</span><span class="p">:</span> <span class="kc">True</span><span class="p">}</span>
<span class="linenos">40</span>
<span class="linenos">41</span> <span class="n">env</span> <span class="o">=</span> <span class="n">fancy_gym</span><span class="o">.</span><span class="n">make_bb</span><span class="p">(</span><span class="n">env_id</span><span class="o">=</span><span class="n">base_env_id</span><span class="p">,</span> <span class="n">wrappers</span><span class="o">=</span><span class="n">wrappers</span><span class="p">,</span> <span class="n">black_box_kwargs</span><span class="o">=</span><span class="n">black_box_kwargs</span><span class="p">,</span>
<span class="linenos">42</span> <span class="n">traj_gen_kwargs</span><span class="o">=</span><span class="n">trajectory_generator_kwargs</span><span class="p">,</span> <span class="n">controller_kwargs</span><span class="o">=</span><span class="n">controller_kwargs</span><span class="p">,</span>
<span class="linenos">43</span> <span class="n">phase_kwargs</span><span class="o">=</span><span class="n">phase_generator_kwargs</span><span class="p">,</span> <span class="n">basis_kwargs</span><span class="o">=</span><span class="n">basis_generator_kwargs</span><span class="p">,</span>
<span class="linenos">44</span> <span class="n">seed</span><span class="o">=</span><span class="n">seed</span><span class="p">)</span>
<span class="linenos">45</span> <span class="k">if</span> <span class="n">render</span><span class="p">:</span>
<span class="linenos">46</span> <span class="n">env</span><span class="o">.</span><span class="n">render</span><span class="p">(</span><span class="n">mode</span><span class="o">=</span><span class="s2">&quot;human&quot;</span><span class="p">)</span>
<span class="linenos">47</span>
<span class="linenos">48</span> <span class="n">obs</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="linenos">49</span>
<span class="linenos">50</span> <span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="n">iteration</span><span class="p">):</span>
<span class="linenos">51</span> <span class="n">ac</span> <span class="o">=</span> <span class="n">env</span><span class="o">.</span><span class="n">action_space</span><span class="o">.</span><span class="n">sample</span><span class="p">()</span>
<span class="linenos">52</span> <span class="n">obs</span><span class="p">,</span> <span class="n">reward</span><span class="p">,</span> <span class="n">terminated</span><span class="p">,</span> <span class="n">truncated</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">step</span><span class="p">(</span><span class="n">ac</span><span class="p">)</span>
<span class="linenos">53</span> <span class="k">if</span> <span class="n">terminated</span> <span class="ow">or</span> <span class="n">truncated</span><span class="p">:</span>
<span class="linenos">54</span> <span class="n">env</span><span class="o">.</span><span class="n">reset</span><span class="p">()</span>
<span class="linenos">55</span>
<span class="linenos">56</span> <span class="n">env</span><span class="o">.</span><span class="n">close</span><span class="p">()</span>
<span class="linenos">57</span> <span class="k">del</span> <span class="n">env</span>
<span class="linenos">58</span>
<span class="linenos">59</span>
<span class="linenos">60</span><span class="k">if</span> <span class="vm">__name__</span> <span class="o">==</span> <span class="s2">&quot;__main__&quot;</span><span class="p">:</span>
<span class="linenos">61</span> <span class="c1"># run a registered replanning environment</span>
<span class="linenos">62</span> <span class="n">example_run_replanning_env</span><span class="p">(</span><span class="n">env_name</span><span class="o">=</span><span class="s2">&quot;fancy_ProDMP/BoxPushingDenseReplan-v0&quot;</span><span class="p">,</span> <span class="n">seed</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span> <span class="n">iterations</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span> <span class="n">render</span><span class="o">=</span><span class="kc">False</span><span class="p">)</span>
<span class="linenos">63</span>
<span class="linenos">64</span> <span class="c1"># run a custom replanning environment</span>
<span class="linenos">65</span> <span class="n">example_custom_replanning_envs</span><span class="p">(</span><span class="n">seed</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="n">iteration</span><span class="o">=</span><span class="mi">8</span><span class="p">,</span> <span class="n">render</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
</pre></div>
</div>
</section>
</div>
</div>
<footer><div class="rst-footer-buttons" role="navigation" aria-label="Footer">
<a href="pd_control_gain_tuning.html" class="btn btn-neutral float-left" title="PD Control Gain Tuning Example" accesskey="p" rel="prev"><span class="fa fa-arrow-circle-left" aria-hidden="true"></span> Previous</a>
<a href="../api.html" class="btn btn-neutral float-right" title="API" accesskey="n" rel="next">Next <span class="fa fa-arrow-circle-right" aria-hidden="true"></span></a>
</div>
<hr/>
<div role="contentinfo">
<p>&#169; Copyright 2020-2024, Fabian Otto, Onur Celik, Dominik Roth, Hongyi Zhou.</p>
</div>
Built with <a href="https://www.sphinx-doc.org/">Sphinx</a> using a
<a href="https://github.com/readthedocs/sphinx_rtd_theme">theme</a>
provided by <a href="https://readthedocs.org">Read the Docs</a>.
</footer>
</div>
</div>
</section>
</div>
<script>
jQuery(function () {
SphinxRtdTheme.Navigation.enable(true);
});
</script>
</body>
</html>
Reference in New Issue View Git Blame Copy Permalink