mirror of
https://github.com/labmlai/annotated_deep_learning_paper_implementations.git
synced 2025-08-18 11:52:00 +08:00
505 lines
30 KiB
HTML
505 lines
30 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="This implements the Atari games with multi-processing."/>
|
|
|
|
<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="Atari wrapper with multi-processing"/>
|
|
<meta name="twitter:description" content="This implements the Atari games with multi-processing."/>
|
|
<meta name="twitter:site" content="@labmlai"/>
|
|
<meta name="twitter:creator" content="@labmlai"/>
|
|
|
|
<meta property="og:url" content="https://nn.labml.ai/rl/game.html"/>
|
|
<meta property="og:title" content="Atari wrapper with multi-processing"/>
|
|
<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="Atari wrapper with multi-processing"/>
|
|
<meta property="og:description" content="This implements the Atari games with multi-processing."/>
|
|
|
|
<title>Atari wrapper with multi-processing</title>
|
|
<link rel="shortcut icon" href="/icon.png"/>
|
|
<link rel="stylesheet" href="../pylit.css">
|
|
<link rel="canonical" href="https://nn.labml.ai/rl/game.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>
|
|
</p>
|
|
<p>
|
|
|
|
<a href="https://github.com/labmlai/annotated_deep_learning_paper_implementations/tree/master/labml_nn/rl/game.py">
|
|
<img alt="Github"
|
|
src="https://img.shields.io/github/stars/labmlai/annotated_deep_learning_paper_implementations?style=social"
|
|
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>Atari wrapper with multi-processing</h1>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">9</span><span></span><span class="kn">import</span> <span class="nn">multiprocessing</span>
|
|
<span class="lineno">10</span><span class="kn">import</span> <span class="nn">multiprocessing.connection</span>
|
|
<span class="lineno">11</span>
|
|
<span class="lineno">12</span><span class="kn">import</span> <span class="nn">cv2</span>
|
|
<span class="lineno">13</span><span class="kn">import</span> <span class="nn">gym</span>
|
|
<span class="lineno">14</span><span class="kn">import</span> <span class="nn">numpy</span> <span class="k">as</span> <span class="nn">np</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-1'>
|
|
<div class='docs doc-strings'>
|
|
<div class='section-link'>
|
|
<a href='#section-1'>#</a>
|
|
</div>
|
|
<h2><a name="game-environment"></a>Game environment</h2>
|
|
<p>This is a wrapper for OpenAI gym game environment.
|
|
We do a few things here:</p>
|
|
<ol>
|
|
<li>Apply the same action on four frames and get the last frame</li>
|
|
<li>Convert observation frames to gray and scale it to (84, 84)</li>
|
|
<li>Stack four frames of the last four actions</li>
|
|
<li>Add episode information (total reward for the entire episode) for monitoring</li>
|
|
<li>Restrict an episode to a single life (game has 5 lives, we reset after every single life)</li>
|
|
</ol>
|
|
<h4>Observation format</h4>
|
|
<p>Observation is tensor of size (4, 84, 84). It is four frames
|
|
(images of the game screen) stacked on first axis.
|
|
i.e, each channel is a frame.</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">17</span><span class="k">class</span> <span class="nc">Game</span><span class="p">:</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-2'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-2'>#</a>
|
|
</div>
|
|
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">35</span> <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">seed</span><span class="p">:</span> <span class="nb">int</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>
|
|
<p>create environment</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">37</span> <span class="bp">self</span><span class="o">.</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="s1">'BreakoutNoFrameskip-v4'</span><span class="p">)</span>
|
|
<span class="lineno">38</span> <span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">seed</span><span class="p">(</span><span class="n">seed</span><span class="p">)</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-4'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-4'>#</a>
|
|
</div>
|
|
<p>tensor for a stack of 4 frames</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">41</span> <span class="bp">self</span><span class="o">.</span><span class="n">obs_4</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="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></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-5'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-5'>#</a>
|
|
</div>
|
|
<p>buffer to keep the maximum of last 2 frames</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">obs_2_max</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="mi">2</span><span class="p">,</span> <span class="mi">84</span><span class="p">,</span> <span class="mi">84</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>
|
|
<p>keep track of the episode rewards</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">47</span> <span class="bp">self</span><span class="o">.</span><span class="n">rewards</span> <span class="o">=</span> <span class="p">[]</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-7'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-7'>#</a>
|
|
</div>
|
|
<p>and number of lives left</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">49</span> <span class="bp">self</span><span class="o">.</span><span class="n">lives</span> <span class="o">=</span> <span class="mi">0</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-8'>
|
|
<div class='docs doc-strings'>
|
|
<div class='section-link'>
|
|
<a href='#section-8'>#</a>
|
|
</div>
|
|
<h3>Step</h3>
|
|
<p>Executes <code>action</code> for 4 time steps and
|
|
returns a tuple of (observation, reward, done, episode_info).</p>
|
|
<ul>
|
|
<li><code>observation</code>: stacked 4 frames (this frame and frames for last 3 actions)</li>
|
|
<li><code>reward</code>: total reward while the action was executed</li>
|
|
<li><code>done</code>: whether the episode finished (a life lost)</li>
|
|
<li><code>episode_info</code>: episode information if completed</li>
|
|
</ul>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">51</span> <span class="k">def</span> <span class="nf">step</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">action</span><span class="p">):</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-9'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-9'>#</a>
|
|
</div>
|
|
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">63</span> <span class="n">reward</span> <span class="o">=</span> <span class="mf">0.</span>
|
|
<span class="lineno">64</span> <span class="n">done</span> <span class="o">=</span> <span class="kc">None</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>run for 4 steps</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">67</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="mi">4</span><span class="p">):</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>execute the action in the OpenAI Gym environment</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">69</span> <span class="n">obs</span><span class="p">,</span> <span class="n">r</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="bp">self</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">action</span><span class="p">)</span>
|
|
<span class="lineno">70</span>
|
|
<span class="lineno">71</span> <span class="k">if</span> <span class="n">i</span> <span class="o">>=</span> <span class="mi">2</span><span class="p">:</span>
|
|
<span class="lineno">72</span> <span class="bp">self</span><span class="o">.</span><span class="n">obs_2_max</span><span class="p">[</span><span class="n">i</span> <span class="o">%</span> <span class="mi">2</span><span class="p">]</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_process_obs</span><span class="p">(</span><span class="n">obs</span><span class="p">)</span>
|
|
<span class="lineno">73</span>
|
|
<span class="lineno">74</span> <span class="n">reward</span> <span class="o">+=</span> <span class="n">r</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>get number of lives left</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">77</span> <span class="n">lives</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">unwrapped</span><span class="o">.</span><span class="n">ale</span><span class="o">.</span><span class="n">lives</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>reset if a life is lost</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">79</span> <span class="k">if</span> <span class="n">lives</span> <span class="o"><</span> <span class="bp">self</span><span class="o">.</span><span class="n">lives</span><span class="p">:</span>
|
|
<span class="lineno">80</span> <span class="n">done</span> <span class="o">=</span> <span class="kc">True</span>
|
|
<span class="lineno">81</span> <span class="k">break</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>maintain rewards for each step</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">84</span> <span class="bp">self</span><span class="o">.</span><span class="n">rewards</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">reward</span><span class="p">)</span>
|
|
<span class="lineno">85</span>
|
|
<span class="lineno">86</span> <span class="k">if</span> <span class="n">done</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>if finished, set episode information if episode is over, and reset</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">88</span> <span class="n">episode_info</span> <span class="o">=</span> <span class="p">{</span><span class="s2">"reward"</span><span class="p">:</span> <span class="nb">sum</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">rewards</span><span class="p">),</span> <span class="s2">"length"</span><span class="p">:</span> <span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">rewards</span><span class="p">)}</span>
|
|
<span class="lineno">89</span> <span class="bp">self</span><span class="o">.</span><span class="n">reset</span><span class="p">()</span>
|
|
<span class="lineno">90</span> <span class="k">else</span><span class="p">:</span>
|
|
<span class="lineno">91</span> <span class="n">episode_info</span> <span class="o">=</span> <span class="kc">None</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>get the max of last two frames</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">94</span> <span class="n">obs</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">obs_2_max</span><span class="o">.</span><span class="n">max</span><span class="p">(</span><span class="n">axis</span><span class="o">=</span><span class="mi">0</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>push it to the stack of 4 frames</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">97</span> <span class="bp">self</span><span class="o">.</span><span class="n">obs_4</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">roll</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">obs_4</span><span class="p">,</span> <span class="n">shift</span><span class="o">=-</span><span class="mi">1</span><span class="p">,</span> <span class="n">axis</span><span class="o">=</span><span class="mi">0</span><span class="p">)</span>
|
|
<span class="lineno">98</span> <span class="bp">self</span><span class="o">.</span><span class="n">obs_4</span><span class="p">[</span><span class="o">-</span><span class="mi">1</span><span class="p">]</span> <span class="o">=</span> <span class="n">obs</span>
|
|
<span class="lineno">99</span>
|
|
<span class="lineno">100</span> <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">obs_4</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">episode_info</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-18'>
|
|
<div class='docs doc-strings'>
|
|
<div class='section-link'>
|
|
<a href='#section-18'>#</a>
|
|
</div>
|
|
<h3>Reset environment</h3>
|
|
<p>Clean up episode info and 4 frame stack</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">102</span> <span class="k">def</span> <span class="nf">reset</span><span class="p">(</span><span class="bp">self</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>reset OpenAI Gym environment</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">109</span> <span class="n">obs</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">reset</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>reset caches</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">112</span> <span class="n">obs</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_process_obs</span><span class="p">(</span><span class="n">obs</span><span class="p">)</span>
|
|
<span class="lineno">113</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="mi">4</span><span class="p">):</span>
|
|
<span class="lineno">114</span> <span class="bp">self</span><span class="o">.</span><span class="n">obs_4</span><span class="p">[</span><span class="n">i</span><span class="p">]</span> <span class="o">=</span> <span class="n">obs</span>
|
|
<span class="lineno">115</span> <span class="bp">self</span><span class="o">.</span><span class="n">rewards</span> <span class="o">=</span> <span class="p">[]</span>
|
|
<span class="lineno">116</span>
|
|
<span class="lineno">117</span> <span class="bp">self</span><span class="o">.</span><span class="n">lives</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">unwrapped</span><span class="o">.</span><span class="n">ale</span><span class="o">.</span><span class="n">lives</span><span class="p">()</span>
|
|
<span class="lineno">118</span>
|
|
<span class="lineno">119</span> <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">obs_4</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-21'>
|
|
<div class='docs doc-strings'>
|
|
<div class='section-link'>
|
|
<a href='#section-21'>#</a>
|
|
</div>
|
|
<h4>Process game frames</h4>
|
|
<p>Convert game frames to gray and rescale to 84x84</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">121</span> <span class="nd">@staticmethod</span>
|
|
<span class="lineno">122</span> <span class="k">def</span> <span class="nf">_process_obs</span><span class="p">(</span><span class="n">obs</span><span class="p">):</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-22'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-22'>#</a>
|
|
</div>
|
|
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">127</span> <span class="n">obs</span> <span class="o">=</span> <span class="n">cv2</span><span class="o">.</span><span class="n">cvtColor</span><span class="p">(</span><span class="n">obs</span><span class="p">,</span> <span class="n">cv2</span><span class="o">.</span><span class="n">COLOR_RGB2GRAY</span><span class="p">)</span>
|
|
<span class="lineno">128</span> <span class="n">obs</span> <span class="o">=</span> <span class="n">cv2</span><span class="o">.</span><span class="n">resize</span><span class="p">(</span><span class="n">obs</span><span class="p">,</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">interpolation</span><span class="o">=</span><span class="n">cv2</span><span class="o">.</span><span class="n">INTER_AREA</span><span class="p">)</span>
|
|
<span class="lineno">129</span> <span class="k">return</span> <span class="n">obs</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-23'>
|
|
<div class='docs doc-strings'>
|
|
<div class='section-link'>
|
|
<a href='#section-23'>#</a>
|
|
</div>
|
|
<h2>Worker Process</h2>
|
|
<p>Each worker process runs this method</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">132</span><span class="k">def</span> <span class="nf">worker_process</span><span class="p">(</span><span class="n">remote</span><span class="p">:</span> <span class="n">multiprocessing</span><span class="o">.</span><span class="n">connection</span><span class="o">.</span><span class="n">Connection</span><span class="p">,</span> <span class="n">seed</span><span class="p">:</span> <span class="nb">int</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>create game</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">140</span> <span class="n">game</span> <span class="o">=</span> <span class="n">Game</span><span class="p">(</span><span class="n">seed</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>wait for instructions from the connection and execute them</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">143</span> <span class="k">while</span> <span class="kc">True</span><span class="p">:</span>
|
|
<span class="lineno">144</span> <span class="n">cmd</span><span class="p">,</span> <span class="n">data</span> <span class="o">=</span> <span class="n">remote</span><span class="o">.</span><span class="n">recv</span><span class="p">()</span>
|
|
<span class="lineno">145</span> <span class="k">if</span> <span class="n">cmd</span> <span class="o">==</span> <span class="s2">"step"</span><span class="p">:</span>
|
|
<span class="lineno">146</span> <span class="n">remote</span><span class="o">.</span><span class="n">send</span><span class="p">(</span><span class="n">game</span><span class="o">.</span><span class="n">step</span><span class="p">(</span><span class="n">data</span><span class="p">))</span>
|
|
<span class="lineno">147</span> <span class="k">elif</span> <span class="n">cmd</span> <span class="o">==</span> <span class="s2">"reset"</span><span class="p">:</span>
|
|
<span class="lineno">148</span> <span class="n">remote</span><span class="o">.</span><span class="n">send</span><span class="p">(</span><span class="n">game</span><span class="o">.</span><span class="n">reset</span><span class="p">())</span>
|
|
<span class="lineno">149</span> <span class="k">elif</span> <span class="n">cmd</span> <span class="o">==</span> <span class="s2">"close"</span><span class="p">:</span>
|
|
<span class="lineno">150</span> <span class="n">remote</span><span class="o">.</span><span class="n">close</span><span class="p">()</span>
|
|
<span class="lineno">151</span> <span class="k">break</span>
|
|
<span class="lineno">152</span> <span class="k">else</span><span class="p">:</span>
|
|
<span class="lineno">153</span> <span class="k">raise</span> <span class="ne">NotImplementedError</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-26'>
|
|
<div class='docs doc-strings'>
|
|
<div class='section-link'>
|
|
<a href='#section-26'>#</a>
|
|
</div>
|
|
<p>Creates a new worker and runs it in a separate process.</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">156</span><span class="k">class</span> <span class="nc">Worker</span><span class="p">:</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-27'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-27'>#</a>
|
|
</div>
|
|
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">161</span> <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">seed</span><span class="p">):</span>
|
|
<span class="lineno">162</span> <span class="bp">self</span><span class="o">.</span><span class="n">child</span><span class="p">,</span> <span class="n">parent</span> <span class="o">=</span> <span class="n">multiprocessing</span><span class="o">.</span><span class="n">Pipe</span><span class="p">()</span>
|
|
<span class="lineno">163</span> <span class="bp">self</span><span class="o">.</span><span class="n">process</span> <span class="o">=</span> <span class="n">multiprocessing</span><span class="o">.</span><span class="n">Process</span><span class="p">(</span><span class="n">target</span><span class="o">=</span><span class="n">worker_process</span><span class="p">,</span> <span class="n">args</span><span class="o">=</span><span class="p">(</span><span class="n">parent</span><span class="p">,</span> <span class="n">seed</span><span class="p">))</span>
|
|
<span class="lineno">164</span> <span class="bp">self</span><span class="o">.</span><span class="n">process</span><span class="o">.</span><span class="n">start</span><span class="p">()</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='footer'>
|
|
<a href="https://papers.labml.ai">Trending Research Papers</a>
|
|
<a href="https://labml.ai">labml.ai</a>
|
|
</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>
|
|
<script>
|
|
function handleImages() {
|
|
var images = document.querySelectorAll('p>img')
|
|
|
|
console.log(images);
|
|
for (var i = 0; i < images.length; ++i) {
|
|
handleImage(images[i])
|
|
}
|
|
}
|
|
|
|
function handleImage(img) {
|
|
img.parentElement.style.textAlign = 'center'
|
|
|
|
var modal = document.createElement('div')
|
|
modal.id = 'modal'
|
|
|
|
var modalContent = document.createElement('div')
|
|
modal.appendChild(modalContent)
|
|
|
|
var modalImage = document.createElement('img')
|
|
modalContent.appendChild(modalImage)
|
|
|
|
var span = document.createElement('span')
|
|
span.classList.add('close')
|
|
span.textContent = 'x'
|
|
modal.appendChild(span)
|
|
|
|
img.onclick = function () {
|
|
console.log('clicked')
|
|
document.body.appendChild(modal)
|
|
modalImage.src = img.src
|
|
}
|
|
|
|
span.onclick = function () {
|
|
document.body.removeChild(modal)
|
|
}
|
|
}
|
|
|
|
handleImages()
|
|
</script>
|
|
</body>
|
|
</html> |