mirror of
https://github.com/labmlai/annotated_deep_learning_paper_implementations.git
synced 2025-10-31 18:58:43 +08:00
948 lines
62 KiB
HTML
948 lines
62 KiB
HTML
<!DOCTYPE html>
|
|
<html>
|
|
<head>
|
|
<meta http-equiv="content-type" content="text/html;charset=utf-8"/>
|
|
<meta name="viewport" content="width=device-width, initial-scale=1.0"/>
|
|
<meta name="description" content="Implementation of DQN experiment with Atari Breakout"/>
|
|
|
|
<meta name="twitter:card" content="summary"/>
|
|
<meta name="twitter:image:src" content="https://avatars1.githubusercontent.com/u/64068543?s=400&v=4"/>
|
|
<meta name="twitter:title" content="DQN Experiment with Atari Breakout"/>
|
|
<meta name="twitter:description" content="Implementation of DQN experiment with Atari Breakout"/>
|
|
<meta name="twitter:site" content="@labmlai"/>
|
|
<meta name="twitter:creator" content="@labmlai"/>
|
|
|
|
<meta property="og:url" content="https://nn.labml.ai/rl/dqn/experiment.html"/>
|
|
<meta property="og:title" content="DQN Experiment with Atari Breakout"/>
|
|
<meta property="og:image" content="https://avatars1.githubusercontent.com/u/64068543?s=400&v=4"/>
|
|
<meta property="og:site_name" content="LabML Neural Networks"/>
|
|
<meta property="og:type" content="object"/>
|
|
<meta property="og:title" content="DQN Experiment with Atari Breakout"/>
|
|
<meta property="og:description" content="Implementation of DQN experiment with Atari Breakout"/>
|
|
|
|
<title>DQN Experiment with Atari Breakout</title>
|
|
<link rel="shortcut icon" href="/icon.png"/>
|
|
<link rel="stylesheet" href="../../pylit.css">
|
|
<link rel="canonical" href="https://nn.labml.ai/rl/dqn/experiment.html"/>
|
|
<!-- Global site tag (gtag.js) - Google Analytics -->
|
|
<script async src="https://www.googletagmanager.com/gtag/js?id=G-4V3HC8HBLH"></script>
|
|
<script>
|
|
window.dataLayer = window.dataLayer || [];
|
|
|
|
function gtag() {
|
|
dataLayer.push(arguments);
|
|
}
|
|
|
|
gtag('js', new Date());
|
|
|
|
gtag('config', 'G-4V3HC8HBLH');
|
|
</script>
|
|
</head>
|
|
<body>
|
|
<div id='container'>
|
|
<div id="background"></div>
|
|
<div class='section'>
|
|
<div class='docs'>
|
|
<p>
|
|
<a class="parent" href="/">home</a>
|
|
<a class="parent" href="../index.html">rl</a>
|
|
<a class="parent" href="index.html">dqn</a>
|
|
</p>
|
|
<p>
|
|
|
|
<a href="https://github.com/lab-ml/labml_nn/tree/master/labml_nn/rl/dqn/experiment.py">
|
|
<img alt="Github"
|
|
src="https://img.shields.io/github/stars/lab-ml/nn?style=social"
|
|
style="max-width:100%;"/></a>
|
|
<a href="https://join.slack.com/t/labforml/shared_invite/zt-egj9zvq9-Dl3hhZqobexgT7aVKnD14g/"
|
|
rel="nofollow">
|
|
<img alt="Join Slact"
|
|
src="https://img.shields.io/badge/slack-chat-green.svg?logo=slack"
|
|
style="max-width:100%;"/></a>
|
|
<a href="https://twitter.com/labmlai"
|
|
rel="nofollow">
|
|
<img alt="Twitter"
|
|
src="https://img.shields.io/twitter/follow/labmlai?style=social"
|
|
style="max-width:100%;"/></a>
|
|
</p>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-0'>
|
|
<div class='docs doc-strings'>
|
|
<div class='section-link'>
|
|
<a href='#section-0'>#</a>
|
|
</div>
|
|
<h1>DQN Experiment with Atari Breakout</h1>
|
|
<p>This experiment trains a Deep Q Network (DQN) to play Atari Breakout game on OpenAI Gym.
|
|
It runs the <a href="../game.html">game environments on multiple processes</a> to sample efficiently.</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">13</span><span></span><span class="kn">import</span> <span class="nn">numpy</span> <span class="k">as</span> <span class="nn">np</span>
|
|
<span class="lineno">14</span><span class="kn">import</span> <span class="nn">torch</span>
|
|
<span class="lineno">15</span>
|
|
<span class="lineno">16</span><span class="kn">from</span> <span class="nn">labml</span> <span class="kn">import</span> <span class="n">tracker</span><span class="p">,</span> <span class="n">experiment</span><span class="p">,</span> <span class="n">logger</span><span class="p">,</span> <span class="n">monit</span>
|
|
<span class="lineno">17</span><span class="kn">from</span> <span class="nn">labml_helpers.schedule</span> <span class="kn">import</span> <span class="n">Piecewise</span>
|
|
<span class="lineno">18</span><span class="kn">from</span> <span class="nn">labml_nn.rl.dqn</span> <span class="kn">import</span> <span class="n">QFuncLoss</span>
|
|
<span class="lineno">19</span><span class="kn">from</span> <span class="nn">labml_nn.rl.dqn.model</span> <span class="kn">import</span> <span class="n">Model</span>
|
|
<span class="lineno">20</span><span class="kn">from</span> <span class="nn">labml_nn.rl.dqn.replay_buffer</span> <span class="kn">import</span> <span class="n">ReplayBuffer</span>
|
|
<span class="lineno">21</span><span class="kn">from</span> <span class="nn">labml_nn.rl.game</span> <span class="kn">import</span> <span class="n">Worker</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-1'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-1'>#</a>
|
|
</div>
|
|
<p>Select device</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">24</span><span class="k">if</span> <span class="n">torch</span><span class="o">.</span><span class="n">cuda</span><span class="o">.</span><span class="n">is_available</span><span class="p">():</span>
|
|
<span class="lineno">25</span> <span class="n">device</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">device</span><span class="p">(</span><span class="s2">"cuda:0"</span><span class="p">)</span>
|
|
<span class="lineno">26</span><span class="k">else</span><span class="p">:</span>
|
|
<span class="lineno">27</span> <span class="n">device</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">device</span><span class="p">(</span><span class="s2">"cpu"</span><span class="p">)</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-2'>
|
|
<div class='docs doc-strings'>
|
|
<div class='section-link'>
|
|
<a href='#section-2'>#</a>
|
|
</div>
|
|
<p>Scale observations from <code>[0, 255]</code> to <code>[0, 1]</code></p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">30</span><span class="k">def</span> <span class="nf">obs_to_torch</span><span class="p">(</span><span class="n">obs</span><span class="p">:</span> <span class="n">np</span><span class="o">.</span><span class="n">ndarray</span><span class="p">)</span> <span class="o">-></span> <span class="n">torch</span><span class="o">.</span><span class="n">Tensor</span><span class="p">:</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-3'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-3'>#</a>
|
|
</div>
|
|
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">32</span> <span class="k">return</span> <span class="n">torch</span><span class="o">.</span><span class="n">tensor</span><span class="p">(</span><span class="n">obs</span><span class="p">,</span> <span class="n">dtype</span><span class="o">=</span><span class="n">torch</span><span class="o">.</span><span class="n">float32</span><span class="p">,</span> <span class="n">device</span><span class="o">=</span><span class="n">device</span><span class="p">)</span> <span class="o">/</span> <span class="mf">255.</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-4'>
|
|
<div class='docs doc-strings'>
|
|
<div class='section-link'>
|
|
<a href='#section-4'>#</a>
|
|
</div>
|
|
<h2>Trainer</h2>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">35</span><span class="k">class</span> <span class="nc">Trainer</span><span class="p">:</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-5'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-5'>#</a>
|
|
</div>
|
|
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">40</span> <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-6'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-6'>#</a>
|
|
</div>
|
|
<h4>Configurations</h4>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-7'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-7'>#</a>
|
|
</div>
|
|
<p>number of workers</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">44</span> <span class="bp">self</span><span class="o">.</span><span class="n">n_workers</span> <span class="o">=</span> <span class="mi">8</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-8'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-8'>#</a>
|
|
</div>
|
|
<p>steps sampled on each update</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">46</span> <span class="bp">self</span><span class="o">.</span><span class="n">worker_steps</span> <span class="o">=</span> <span class="mi">4</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-9'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-9'>#</a>
|
|
</div>
|
|
<p>number of training iterations</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">48</span> <span class="bp">self</span><span class="o">.</span><span class="n">train_epochs</span> <span class="o">=</span> <span class="mi">8</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-10'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-10'>#</a>
|
|
</div>
|
|
<p>number of updates</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">51</span> <span class="bp">self</span><span class="o">.</span><span class="n">updates</span> <span class="o">=</span> <span class="mi">1_000_000</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-11'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-11'>#</a>
|
|
</div>
|
|
<p>size of mini batch for training</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">53</span> <span class="bp">self</span><span class="o">.</span><span class="n">mini_batch_size</span> <span class="o">=</span> <span class="mi">32</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-12'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-12'>#</a>
|
|
</div>
|
|
<p>exploration as a function of updates</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">56</span> <span class="bp">self</span><span class="o">.</span><span class="n">exploration_coefficient</span> <span class="o">=</span> <span class="n">Piecewise</span><span class="p">(</span>
|
|
<span class="lineno">57</span> <span class="p">[</span>
|
|
<span class="lineno">58</span> <span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="mf">1.0</span><span class="p">),</span>
|
|
<span class="lineno">59</span> <span class="p">(</span><span class="mi">25_000</span><span class="p">,</span> <span class="mf">0.1</span><span class="p">),</span>
|
|
<span class="lineno">60</span> <span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">updates</span> <span class="o">/</span> <span class="mi">2</span><span class="p">,</span> <span class="mf">0.01</span><span class="p">)</span>
|
|
<span class="lineno">61</span> <span class="p">],</span> <span class="n">outside_value</span><span class="o">=</span><span class="mf">0.01</span><span class="p">)</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-13'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-13'>#</a>
|
|
</div>
|
|
<p>update target network every 250 update</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">64</span> <span class="bp">self</span><span class="o">.</span><span class="n">update_target_model</span> <span class="o">=</span> <span class="mi">250</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-14'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-14'>#</a>
|
|
</div>
|
|
<p>$\beta$ for replay buffer as a function of updates</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">67</span> <span class="bp">self</span><span class="o">.</span><span class="n">prioritized_replay_beta</span> <span class="o">=</span> <span class="n">Piecewise</span><span class="p">(</span>
|
|
<span class="lineno">68</span> <span class="p">[</span>
|
|
<span class="lineno">69</span> <span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="mf">0.4</span><span class="p">),</span>
|
|
<span class="lineno">70</span> <span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">updates</span><span class="p">,</span> <span class="mi">1</span><span class="p">)</span>
|
|
<span class="lineno">71</span> <span class="p">],</span> <span class="n">outside_value</span><span class="o">=</span><span class="mi">1</span><span class="p">)</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-15'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-15'>#</a>
|
|
</div>
|
|
<p>Replay buffer with $\alpha = 0.6$. Capacity of the replay buffer must be a power of 2.</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">74</span> <span class="bp">self</span><span class="o">.</span><span class="n">replay_buffer</span> <span class="o">=</span> <span class="n">ReplayBuffer</span><span class="p">(</span><span class="mi">2</span> <span class="o">**</span> <span class="mi">14</span><span class="p">,</span> <span class="mf">0.6</span><span class="p">)</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-16'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-16'>#</a>
|
|
</div>
|
|
<p>Model for sampling and training</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">77</span> <span class="bp">self</span><span class="o">.</span><span class="n">model</span> <span class="o">=</span> <span class="n">Model</span><span class="p">()</span><span class="o">.</span><span class="n">to</span><span class="p">(</span><span class="n">device</span><span class="p">)</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-17'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-17'>#</a>
|
|
</div>
|
|
<p>target model to get $\color{orange}Q(s’;\color{orange}{\theta_i^{-}})$</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">79</span> <span class="bp">self</span><span class="o">.</span><span class="n">target_model</span> <span class="o">=</span> <span class="n">Model</span><span class="p">()</span><span class="o">.</span><span class="n">to</span><span class="p">(</span><span class="n">device</span><span class="p">)</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-18'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-18'>#</a>
|
|
</div>
|
|
<p>create workers</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">82</span> <span class="bp">self</span><span class="o">.</span><span class="n">workers</span> <span class="o">=</span> <span class="p">[</span><span class="n">Worker</span><span class="p">(</span><span class="mi">47</span> <span class="o">+</span> <span class="n">i</span><span class="p">)</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="bp">self</span><span class="o">.</span><span class="n">n_workers</span><span class="p">)]</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-19'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-19'>#</a>
|
|
</div>
|
|
<p>initialize tensors for observations</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">85</span> <span class="bp">self</span><span class="o">.</span><span class="n">obs</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">zeros</span><span class="p">((</span><span class="bp">self</span><span class="o">.</span><span class="n">n_workers</span><span class="p">,</span> <span class="mi">4</span><span class="p">,</span> <span class="mi">84</span><span class="p">,</span> <span class="mi">84</span><span class="p">),</span> <span class="n">dtype</span><span class="o">=</span><span class="n">np</span><span class="o">.</span><span class="n">uint8</span><span class="p">)</span>
|
|
<span class="lineno">86</span> <span class="k">for</span> <span class="n">worker</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">workers</span><span class="p">:</span>
|
|
<span class="lineno">87</span> <span class="n">worker</span><span class="o">.</span><span class="n">child</span><span class="o">.</span><span class="n">send</span><span class="p">((</span><span class="s2">"reset"</span><span class="p">,</span> <span class="kc">None</span><span class="p">))</span>
|
|
<span class="lineno">88</span> <span class="k">for</span> <span class="n">i</span><span class="p">,</span> <span class="n">worker</span> <span class="ow">in</span> <span class="nb">enumerate</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">workers</span><span class="p">):</span>
|
|
<span class="lineno">89</span> <span class="bp">self</span><span class="o">.</span><span class="n">obs</span><span class="p">[</span><span class="n">i</span><span class="p">]</span> <span class="o">=</span> <span class="n">worker</span><span class="o">.</span><span class="n">child</span><span class="o">.</span><span class="n">recv</span><span class="p">()</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-20'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-20'>#</a>
|
|
</div>
|
|
<p>loss function</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">92</span> <span class="bp">self</span><span class="o">.</span><span class="n">loss_func</span> <span class="o">=</span> <span class="n">QFuncLoss</span><span class="p">(</span><span class="mf">0.99</span><span class="p">)</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-21'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-21'>#</a>
|
|
</div>
|
|
<p>optimizer</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">94</span> <span class="bp">self</span><span class="o">.</span><span class="n">optimizer</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">optim</span><span class="o">.</span><span class="n">Adam</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="o">.</span><span class="n">parameters</span><span class="p">(),</span> <span class="n">lr</span><span class="o">=</span><span class="mf">2.5e-4</span><span class="p">)</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-22'>
|
|
<div class='docs doc-strings'>
|
|
<div class='section-link'>
|
|
<a href='#section-22'>#</a>
|
|
</div>
|
|
<h4>$\epsilon$-greedy Sampling</h4>
|
|
<p>When sampling actions we use a $\epsilon$-greedy strategy, where we
|
|
take a greedy action with probabiliy $1 - \epsilon$ and
|
|
take a random action with probability $\epsilon$.
|
|
We refer to $\epsilon$ as <code>exploration_coefficient</code>.</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">96</span> <span class="k">def</span> <span class="nf">_sample_action</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">q_value</span><span class="p">:</span> <span class="n">torch</span><span class="o">.</span><span class="n">Tensor</span><span class="p">,</span> <span class="n">exploration_coefficient</span><span class="p">:</span> <span class="nb">float</span><span class="p">):</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-23'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-23'>#</a>
|
|
</div>
|
|
<p>Sampling doesn’t need gradients</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">106</span> <span class="k">with</span> <span class="n">torch</span><span class="o">.</span><span class="n">no_grad</span><span class="p">():</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-24'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-24'>#</a>
|
|
</div>
|
|
<p>Sample the action with highest Q-value. This is the greedy action.</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">108</span> <span class="n">greedy_action</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">argmax</span><span class="p">(</span><span class="n">q_value</span><span class="p">,</span> <span class="n">dim</span><span class="o">=-</span><span class="mi">1</span><span class="p">)</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-25'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-25'>#</a>
|
|
</div>
|
|
<p>Uniformly sample and action</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">110</span> <span class="n">random_action</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">randint</span><span class="p">(</span><span class="n">q_value</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="o">-</span><span class="mi">1</span><span class="p">],</span> <span class="n">greedy_action</span><span class="o">.</span><span class="n">shape</span><span class="p">,</span> <span class="n">device</span><span class="o">=</span><span class="n">q_value</span><span class="o">.</span><span class="n">device</span><span class="p">)</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-26'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-26'>#</a>
|
|
</div>
|
|
<p>Whether to chose greedy action or the random action</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">112</span> <span class="n">is_choose_rand</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">rand</span><span class="p">(</span><span class="n">greedy_action</span><span class="o">.</span><span class="n">shape</span><span class="p">,</span> <span class="n">device</span><span class="o">=</span><span class="n">q_value</span><span class="o">.</span><span class="n">device</span><span class="p">)</span> <span class="o"><</span> <span class="n">exploration_coefficient</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-27'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-27'>#</a>
|
|
</div>
|
|
<p>Pick the action based on <code>is_choose_rand</code></p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">114</span> <span class="k">return</span> <span class="n">torch</span><span class="o">.</span><span class="n">where</span><span class="p">(</span><span class="n">is_choose_rand</span><span class="p">,</span> <span class="n">random_action</span><span class="p">,</span> <span class="n">greedy_action</span><span class="p">)</span><span class="o">.</span><span class="n">cpu</span><span class="p">()</span><span class="o">.</span><span class="n">numpy</span><span class="p">()</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-28'>
|
|
<div class='docs doc-strings'>
|
|
<div class='section-link'>
|
|
<a href='#section-28'>#</a>
|
|
</div>
|
|
<h3>Sample data</h3>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">116</span> <span class="k">def</span> <span class="nf">sample</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">exploration_coefficient</span><span class="p">:</span> <span class="nb">float</span><span class="p">):</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-29'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-29'>#</a>
|
|
</div>
|
|
<p>This doesn’t need gradients</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">120</span> <span class="k">with</span> <span class="n">torch</span><span class="o">.</span><span class="n">no_grad</span><span class="p">():</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-30'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-30'>#</a>
|
|
</div>
|
|
<p>Sample <code>worker_steps</code></p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">122</span> <span class="k">for</span> <span class="n">t</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">worker_steps</span><span class="p">):</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-31'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-31'>#</a>
|
|
</div>
|
|
<p>Get Q_values for the current observation</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">124</span> <span class="n">q_value</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="p">(</span><span class="n">obs_to_torch</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">obs</span><span class="p">))</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-32'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-32'>#</a>
|
|
</div>
|
|
<p>Sample actions</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">126</span> <span class="n">actions</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_sample_action</span><span class="p">(</span><span class="n">q_value</span><span class="p">,</span> <span class="n">exploration_coefficient</span><span class="p">)</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-33'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-33'>#</a>
|
|
</div>
|
|
<p>Run sampled actions on each worker</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">129</span> <span class="k">for</span> <span class="n">w</span><span class="p">,</span> <span class="n">worker</span> <span class="ow">in</span> <span class="nb">enumerate</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">workers</span><span class="p">):</span>
|
|
<span class="lineno">130</span> <span class="n">worker</span><span class="o">.</span><span class="n">child</span><span class="o">.</span><span class="n">send</span><span class="p">((</span><span class="s2">"step"</span><span class="p">,</span> <span class="n">actions</span><span class="p">[</span><span class="n">w</span><span class="p">]))</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-34'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-34'>#</a>
|
|
</div>
|
|
<p>Collect information from each worker</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">133</span> <span class="k">for</span> <span class="n">w</span><span class="p">,</span> <span class="n">worker</span> <span class="ow">in</span> <span class="nb">enumerate</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">workers</span><span class="p">):</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-35'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-35'>#</a>
|
|
</div>
|
|
<p>Get results after executing the actions</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">135</span> <span class="n">next_obs</span><span class="p">,</span> <span class="n">reward</span><span class="p">,</span> <span class="n">done</span><span class="p">,</span> <span class="n">info</span> <span class="o">=</span> <span class="n">worker</span><span class="o">.</span><span class="n">child</span><span class="o">.</span><span class="n">recv</span><span class="p">()</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-36'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-36'>#</a>
|
|
</div>
|
|
<p>Add transition to replay buffer</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">138</span> <span class="bp">self</span><span class="o">.</span><span class="n">replay_buffer</span><span class="o">.</span><span class="n">add</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">obs</span><span class="p">[</span><span class="n">w</span><span class="p">],</span> <span class="n">actions</span><span class="p">[</span><span class="n">w</span><span class="p">],</span> <span class="n">reward</span><span class="p">,</span> <span class="n">next_obs</span><span class="p">,</span> <span class="n">done</span><span class="p">)</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-37'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-37'>#</a>
|
|
</div>
|
|
<p>update episode information
|
|
collect episode info, which is available if an episode finished;
|
|
this includes total reward and length of the episode -
|
|
look at <code>Game</code> to see how it works.</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">144</span> <span class="k">if</span> <span class="n">info</span><span class="p">:</span>
|
|
<span class="lineno">145</span> <span class="n">tracker</span><span class="o">.</span><span class="n">add</span><span class="p">(</span><span class="s1">'reward'</span><span class="p">,</span> <span class="n">info</span><span class="p">[</span><span class="s1">'reward'</span><span class="p">])</span>
|
|
<span class="lineno">146</span> <span class="n">tracker</span><span class="o">.</span><span class="n">add</span><span class="p">(</span><span class="s1">'length'</span><span class="p">,</span> <span class="n">info</span><span class="p">[</span><span class="s1">'length'</span><span class="p">])</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-38'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-38'>#</a>
|
|
</div>
|
|
<p>update current observation</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">149</span> <span class="bp">self</span><span class="o">.</span><span class="n">obs</span><span class="p">[</span><span class="n">w</span><span class="p">]</span> <span class="o">=</span> <span class="n">next_obs</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-39'>
|
|
<div class='docs doc-strings'>
|
|
<div class='section-link'>
|
|
<a href='#section-39'>#</a>
|
|
</div>
|
|
<h3>Train the model</h3>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">151</span> <span class="k">def</span> <span class="nf">train</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">beta</span><span class="p">:</span> <span class="nb">float</span><span class="p">):</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-40'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-40'>#</a>
|
|
</div>
|
|
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">155</span> <span class="k">for</span> <span class="n">_</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">train_epochs</span><span class="p">):</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-41'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-41'>#</a>
|
|
</div>
|
|
<p>Sample from priority replay buffer</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">157</span> <span class="n">samples</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">replay_buffer</span><span class="o">.</span><span class="n">sample</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">mini_batch_size</span><span class="p">,</span> <span class="n">beta</span><span class="p">)</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-42'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-42'>#</a>
|
|
</div>
|
|
<p>Get the predicted Q-value</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">159</span> <span class="n">q_value</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="p">(</span><span class="n">obs_to_torch</span><span class="p">(</span><span class="n">samples</span><span class="p">[</span><span class="s1">'obs'</span><span class="p">]))</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-43'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-43'>#</a>
|
|
</div>
|
|
<p>Get the Q-values of the next state for <a href="index.html">Double Q-learning</a>.
|
|
Gradients shouldn’t propagate for these</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">163</span> <span class="k">with</span> <span class="n">torch</span><span class="o">.</span><span class="n">no_grad</span><span class="p">():</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-44'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-44'>#</a>
|
|
</div>
|
|
<p>Get $\color{cyan}Q(s’;\color{cyan}{\theta_i})$</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">165</span> <span class="n">double_q_value</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="p">(</span><span class="n">obs_to_torch</span><span class="p">(</span><span class="n">samples</span><span class="p">[</span><span class="s1">'next_obs'</span><span class="p">]))</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-45'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-45'>#</a>
|
|
</div>
|
|
<p>Get $\color{orange}Q(s’;\color{orange}{\theta_i^{-}})$</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">167</span> <span class="n">target_q_value</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">target_model</span><span class="p">(</span><span class="n">obs_to_torch</span><span class="p">(</span><span class="n">samples</span><span class="p">[</span><span class="s1">'next_obs'</span><span class="p">]))</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-46'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-46'>#</a>
|
|
</div>
|
|
<p>Compute Temporal Difference (TD) errors, $\delta$, and the loss, $\mathcal{L}(\theta)$.</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">170</span> <span class="n">td_errors</span><span class="p">,</span> <span class="n">loss</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">loss_func</span><span class="p">(</span><span class="n">q_value</span><span class="p">,</span>
|
|
<span class="lineno">171</span> <span class="n">q_value</span><span class="o">.</span><span class="n">new_tensor</span><span class="p">(</span><span class="n">samples</span><span class="p">[</span><span class="s1">'action'</span><span class="p">]),</span>
|
|
<span class="lineno">172</span> <span class="n">double_q_value</span><span class="p">,</span> <span class="n">target_q_value</span><span class="p">,</span>
|
|
<span class="lineno">173</span> <span class="n">q_value</span><span class="o">.</span><span class="n">new_tensor</span><span class="p">(</span><span class="n">samples</span><span class="p">[</span><span class="s1">'done'</span><span class="p">]),</span>
|
|
<span class="lineno">174</span> <span class="n">q_value</span><span class="o">.</span><span class="n">new_tensor</span><span class="p">(</span><span class="n">samples</span><span class="p">[</span><span class="s1">'reward'</span><span class="p">]),</span>
|
|
<span class="lineno">175</span> <span class="n">q_value</span><span class="o">.</span><span class="n">new_tensor</span><span class="p">(</span><span class="n">samples</span><span class="p">[</span><span class="s1">'weights'</span><span class="p">]))</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-47'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-47'>#</a>
|
|
</div>
|
|
<p>Calculate priorities for replay buffer $p_i = |\delta_i| + \epsilon$</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">178</span> <span class="n">new_priorities</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">abs</span><span class="p">(</span><span class="n">td_errors</span><span class="o">.</span><span class="n">cpu</span><span class="p">()</span><span class="o">.</span><span class="n">numpy</span><span class="p">())</span> <span class="o">+</span> <span class="mf">1e-6</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-48'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-48'>#</a>
|
|
</div>
|
|
<p>Update replay buffer priorities</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">180</span> <span class="bp">self</span><span class="o">.</span><span class="n">replay_buffer</span><span class="o">.</span><span class="n">update_priorities</span><span class="p">(</span><span class="n">samples</span><span class="p">[</span><span class="s1">'indexes'</span><span class="p">],</span> <span class="n">new_priorities</span><span class="p">)</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-49'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-49'>#</a>
|
|
</div>
|
|
<p>Zero out the previously calculated gradients</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">183</span> <span class="bp">self</span><span class="o">.</span><span class="n">optimizer</span><span class="o">.</span><span class="n">zero_grad</span><span class="p">()</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-50'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-50'>#</a>
|
|
</div>
|
|
<p>Calculate gradients</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">185</span> <span class="n">loss</span><span class="o">.</span><span class="n">backward</span><span class="p">()</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-51'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-51'>#</a>
|
|
</div>
|
|
<p>Clip gradients</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">187</span> <span class="n">torch</span><span class="o">.</span><span class="n">nn</span><span class="o">.</span><span class="n">utils</span><span class="o">.</span><span class="n">clip_grad_norm_</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="o">.</span><span class="n">parameters</span><span class="p">(),</span> <span class="n">max_norm</span><span class="o">=</span><span class="mf">0.5</span><span class="p">)</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-52'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-52'>#</a>
|
|
</div>
|
|
<p>Update parameters based on gradients</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">189</span> <span class="bp">self</span><span class="o">.</span><span class="n">optimizer</span><span class="o">.</span><span class="n">step</span><span class="p">()</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-53'>
|
|
<div class='docs doc-strings'>
|
|
<div class='section-link'>
|
|
<a href='#section-53'>#</a>
|
|
</div>
|
|
<h3>Run training loop</h3>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">191</span> <span class="k">def</span> <span class="nf">run_training_loop</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-54'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-54'>#</a>
|
|
</div>
|
|
<p>Last 100 episode information</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">197</span> <span class="n">tracker</span><span class="o">.</span><span class="n">set_queue</span><span class="p">(</span><span class="s1">'reward'</span><span class="p">,</span> <span class="mi">100</span><span class="p">,</span> <span class="kc">True</span><span class="p">)</span>
|
|
<span class="lineno">198</span> <span class="n">tracker</span><span class="o">.</span><span class="n">set_queue</span><span class="p">(</span><span class="s1">'length'</span><span class="p">,</span> <span class="mi">100</span><span class="p">,</span> <span class="kc">True</span><span class="p">)</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-55'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-55'>#</a>
|
|
</div>
|
|
<p>Copy to target network initially</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">201</span> <span class="bp">self</span><span class="o">.</span><span class="n">target_model</span><span class="o">.</span><span class="n">load_state_dict</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="o">.</span><span class="n">state_dict</span><span class="p">())</span>
|
|
<span class="lineno">202</span>
|
|
<span class="lineno">203</span> <span class="k">for</span> <span class="n">update</span> <span class="ow">in</span> <span class="n">monit</span><span class="o">.</span><span class="n">loop</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">updates</span><span class="p">):</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-56'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-56'>#</a>
|
|
</div>
|
|
<p>$\epsilon$, exploration fraction</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">205</span> <span class="n">exploration</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">exploration_coefficient</span><span class="p">(</span><span class="n">update</span><span class="p">)</span>
|
|
<span class="lineno">206</span> <span class="n">tracker</span><span class="o">.</span><span class="n">add</span><span class="p">(</span><span class="s1">'exploration'</span><span class="p">,</span> <span class="n">exploration</span><span class="p">)</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-57'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-57'>#</a>
|
|
</div>
|
|
<p>$\beta$ for prioritized replay</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">208</span> <span class="n">beta</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">prioritized_replay_beta</span><span class="p">(</span><span class="n">update</span><span class="p">)</span>
|
|
<span class="lineno">209</span> <span class="n">tracker</span><span class="o">.</span><span class="n">add</span><span class="p">(</span><span class="s1">'beta'</span><span class="p">,</span> <span class="n">beta</span><span class="p">)</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-58'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-58'>#</a>
|
|
</div>
|
|
<p>Sample with current policy</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">212</span> <span class="bp">self</span><span class="o">.</span><span class="n">sample</span><span class="p">(</span><span class="n">exploration</span><span class="p">)</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-59'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-59'>#</a>
|
|
</div>
|
|
<p>Start training after the buffer is full</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">215</span> <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">replay_buffer</span><span class="o">.</span><span class="n">is_full</span><span class="p">():</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-60'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-60'>#</a>
|
|
</div>
|
|
<p>Train the model</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">217</span> <span class="bp">self</span><span class="o">.</span><span class="n">train</span><span class="p">(</span><span class="n">beta</span><span class="p">)</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-61'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-61'>#</a>
|
|
</div>
|
|
<p>Periodically update target network</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">220</span> <span class="k">if</span> <span class="n">update</span> <span class="o">%</span> <span class="bp">self</span><span class="o">.</span><span class="n">update_target_model</span> <span class="o">==</span> <span class="mi">0</span><span class="p">:</span>
|
|
<span class="lineno">221</span> <span class="bp">self</span><span class="o">.</span><span class="n">target_model</span><span class="o">.</span><span class="n">load_state_dict</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="o">.</span><span class="n">state_dict</span><span class="p">())</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-62'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-62'>#</a>
|
|
</div>
|
|
<p>Save tracked indicators.</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">224</span> <span class="n">tracker</span><span class="o">.</span><span class="n">save</span><span class="p">()</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-63'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-63'>#</a>
|
|
</div>
|
|
<p>Add a new line to the screen periodically</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">226</span> <span class="k">if</span> <span class="p">(</span><span class="n">update</span> <span class="o">+</span> <span class="mi">1</span><span class="p">)</span> <span class="o">%</span> <span class="mi">1_000</span> <span class="o">==</span> <span class="mi">0</span><span class="p">:</span>
|
|
<span class="lineno">227</span> <span class="n">logger</span><span class="o">.</span><span class="n">log</span><span class="p">()</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-64'>
|
|
<div class='docs doc-strings'>
|
|
<div class='section-link'>
|
|
<a href='#section-64'>#</a>
|
|
</div>
|
|
<h3>Destroy</h3>
|
|
<p>Stop the workers</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">229</span> <span class="k">def</span> <span class="nf">destroy</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-65'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-65'>#</a>
|
|
</div>
|
|
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">234</span> <span class="k">for</span> <span class="n">worker</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">workers</span><span class="p">:</span>
|
|
<span class="lineno">235</span> <span class="n">worker</span><span class="o">.</span><span class="n">child</span><span class="o">.</span><span class="n">send</span><span class="p">((</span><span class="s2">"close"</span><span class="p">,</span> <span class="kc">None</span><span class="p">))</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-66'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-66'>#</a>
|
|
</div>
|
|
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">238</span><span class="k">def</span> <span class="nf">main</span><span class="p">():</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-67'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-67'>#</a>
|
|
</div>
|
|
<p>Create the experiment</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">240</span> <span class="n">experiment</span><span class="o">.</span><span class="n">create</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="s1">'dqn'</span><span class="p">)</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-68'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-68'>#</a>
|
|
</div>
|
|
<p>Initialize the trainer</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">242</span> <span class="n">m</span> <span class="o">=</span> <span class="n">Trainer</span><span class="p">()</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-69'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-69'>#</a>
|
|
</div>
|
|
<p>Run and monitor the experiment</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">244</span> <span class="k">with</span> <span class="n">experiment</span><span class="o">.</span><span class="n">start</span><span class="p">():</span>
|
|
<span class="lineno">245</span> <span class="n">m</span><span class="o">.</span><span class="n">run_training_loop</span><span class="p">()</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-70'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-70'>#</a>
|
|
</div>
|
|
<p>Stop the workers</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">247</span> <span class="n">m</span><span class="o">.</span><span class="n">destroy</span><span class="p">()</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-71'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-71'>#</a>
|
|
</div>
|
|
<h2>Run it</h2>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">251</span><span class="k">if</span> <span class="vm">__name__</span> <span class="o">==</span> <span class="s2">"__main__"</span><span class="p">:</span>
|
|
<span class="lineno">252</span> <span class="n">main</span><span class="p">()</span></pre></div>
|
|
</div>
|
|
</div>
|
|
</div>
|
|
</div>
|
|
<script src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.4/MathJax.js?config=TeX-AMS_HTML">
|
|
</script>
|
|
<!-- MathJax configuration -->
|
|
<script type="text/x-mathjax-config">
|
|
MathJax.Hub.Config({
|
|
tex2jax: {
|
|
inlineMath: [ ['$','$'] ],
|
|
displayMath: [ ['$$','$$'] ],
|
|
processEscapes: true,
|
|
processEnvironments: true
|
|
},
|
|
// Center justify equations in code and markdown cells. Elsewhere
|
|
// we use CSS to left justify single line equations in code cells.
|
|
displayAlign: 'center',
|
|
"HTML-CSS": { fonts: ["TeX"] }
|
|
});
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
</script>
|
|
</body>
|
|
</html> |