mirror of
https://github.com/labmlai/annotated_deep_learning_paper_implementations.git
synced 2025-11-02 13:00:17 +08:00
dqn experiment
This commit is contained in:
Varuna Jayasiri
@ -68,12 +68,14 @@
|
||||
<a href='#section-0'>#</a>
|
||||
</div>
|
||||
<h1>Deep Q Network (DQN) Model</h1>
|
||||
<p><a href="https://colab.research.google.com/github/labmlai/annotated_deep_learning_paper_implementations/blob/master/labml_nn/rl/dqn/experiment.ipynb"><img alt="Open In Colab" src="https://colab.research.google.com/assets/colab-badge.svg" /></a>
|
||||
<a href="https://app.labml.ai/run/a0da8048235511ecb9affd797fa27714"><img alt="View Run" src="https://img.shields.io/badge/labml-experiment-brightgreen" /></a></p>
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">10</span><span></span><span class="kn">import</span> <span class="nn">torch</span>
|
||||
<span class="lineno">11</span><span class="kn">from</span> <span class="nn">torch</span> <span class="kn">import</span> <span class="n">nn</span>
|
||||
<span class="lineno">12</span>
|
||||
<span class="lineno">13</span><span class="kn">from</span> <span class="nn">labml_helpers.module</span> <span class="kn">import</span> <span class="n">Module</span></pre></div>
|
||||
<div class="highlight"><pre><span class="lineno">13</span><span></span><span class="kn">import</span> <span class="nn">torch</span>
|
||||
<span class="lineno">14</span><span class="kn">from</span> <span class="nn">torch</span> <span class="kn">import</span> <span class="n">nn</span>
|
||||
<span class="lineno">15</span>
|
||||
<span class="lineno">16</span><span class="kn">from</span> <span class="nn">labml_helpers.module</span> <span class="kn">import</span> <span class="n">Module</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-1'>
|
||||
@ -109,7 +111,7 @@ and in some states the action is significant. Dueling network allows
|
||||
We share the initial layers of the $V$ and $A$ networks.</p>
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">16</span><span class="k">class</span> <span class="nc">Model</span><span class="p">(</span><span class="n">Module</span><span class="p">):</span></pre></div>
|
||||
<div class="highlight"><pre><span class="lineno">19</span><span class="k">class</span> <span class="nc">Model</span><span class="p">(</span><span class="n">Module</span><span class="p">):</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-2'>
|
||||
@ -120,9 +122,9 @@ We share the initial layers of the $V$ and $A$ networks.</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">47</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="lineno">48</span> <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">()</span>
|
||||
<span class="lineno">49</span> <span class="bp">self</span><span class="o">.</span><span class="n">conv</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">Sequential</span><span class="p">(</span></pre></div>
|
||||
<div class="highlight"><pre><span class="lineno">50</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="lineno">51</span> <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">()</span>
|
||||
<span class="lineno">52</span> <span class="bp">self</span><span class="o">.</span><span class="n">conv</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">Sequential</span><span class="p">(</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-3'>
|
||||
@ -134,8 +136,8 @@ We share the initial layers of the $V$ and $A$ networks.</p>
|
||||
$84\times84$ frame and produces a $20\times20$ frame</p>
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">52</span> <span class="n">nn</span><span class="o">.</span><span class="n">Conv2d</span><span class="p">(</span><span class="n">in_channels</span><span class="o">=</span><span class="mi">4</span><span class="p">,</span> <span class="n">out_channels</span><span class="o">=</span><span class="mi">32</span><span class="p">,</span> <span class="n">kernel_size</span><span class="o">=</span><span class="mi">8</span><span class="p">,</span> <span class="n">stride</span><span class="o">=</span><span class="mi">4</span><span class="p">),</span>
|
||||
<span class="lineno">53</span> <span class="n">nn</span><span class="o">.</span><span class="n">ReLU</span><span class="p">(),</span></pre></div>
|
||||
<div class="highlight"><pre><span class="lineno">55</span> <span class="n">nn</span><span class="o">.</span><span class="n">Conv2d</span><span class="p">(</span><span class="n">in_channels</span><span class="o">=</span><span class="mi">4</span><span class="p">,</span> <span class="n">out_channels</span><span class="o">=</span><span class="mi">32</span><span class="p">,</span> <span class="n">kernel_size</span><span class="o">=</span><span class="mi">8</span><span class="p">,</span> <span class="n">stride</span><span class="o">=</span><span class="mi">4</span><span class="p">),</span>
|
||||
<span class="lineno">56</span> <span class="n">nn</span><span class="o">.</span><span class="n">ReLU</span><span class="p">(),</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-4'>
|
||||
@ -147,8 +149,8 @@ $84\times84$ frame and produces a $20\times20$ frame</p>
|
||||
$20\times20$ frame and produces a $9\times9$ frame</p>
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">57</span> <span class="n">nn</span><span class="o">.</span><span class="n">Conv2d</span><span class="p">(</span><span class="n">in_channels</span><span class="o">=</span><span class="mi">32</span><span class="p">,</span> <span class="n">out_channels</span><span class="o">=</span><span class="mi">64</span><span class="p">,</span> <span class="n">kernel_size</span><span class="o">=</span><span class="mi">4</span><span class="p">,</span> <span class="n">stride</span><span class="o">=</span><span class="mi">2</span><span class="p">),</span>
|
||||
<span class="lineno">58</span> <span class="n">nn</span><span class="o">.</span><span class="n">ReLU</span><span class="p">(),</span></pre></div>
|
||||
<div class="highlight"><pre><span class="lineno">60</span> <span class="n">nn</span><span class="o">.</span><span class="n">Conv2d</span><span class="p">(</span><span class="n">in_channels</span><span class="o">=</span><span class="mi">32</span><span class="p">,</span> <span class="n">out_channels</span><span class="o">=</span><span class="mi">64</span><span class="p">,</span> <span class="n">kernel_size</span><span class="o">=</span><span class="mi">4</span><span class="p">,</span> <span class="n">stride</span><span class="o">=</span><span class="mi">2</span><span class="p">),</span>
|
||||
<span class="lineno">61</span> <span class="n">nn</span><span class="o">.</span><span class="n">ReLU</span><span class="p">(),</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-5'>
|
||||
@ -160,9 +162,9 @@ $20\times20$ frame and produces a $9\times9$ frame</p>
|
||||
$9\times9$ frame and produces a $7\times7$ frame</p>
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">62</span> <span class="n">nn</span><span class="o">.</span><span class="n">Conv2d</span><span class="p">(</span><span class="n">in_channels</span><span class="o">=</span><span class="mi">64</span><span class="p">,</span> <span class="n">out_channels</span><span class="o">=</span><span class="mi">64</span><span class="p">,</span> <span class="n">kernel_size</span><span class="o">=</span><span class="mi">3</span><span class="p">,</span> <span class="n">stride</span><span class="o">=</span><span class="mi">1</span><span class="p">),</span>
|
||||
<span class="lineno">63</span> <span class="n">nn</span><span class="o">.</span><span class="n">ReLU</span><span class="p">(),</span>
|
||||
<span class="lineno">64</span> <span class="p">)</span></pre></div>
|
||||
<div class="highlight"><pre><span class="lineno">65</span> <span class="n">nn</span><span class="o">.</span><span class="n">Conv2d</span><span class="p">(</span><span class="n">in_channels</span><span class="o">=</span><span class="mi">64</span><span class="p">,</span> <span class="n">out_channels</span><span class="o">=</span><span class="mi">64</span><span class="p">,</span> <span class="n">kernel_size</span><span class="o">=</span><span class="mi">3</span><span class="p">,</span> <span class="n">stride</span><span class="o">=</span><span class="mi">1</span><span class="p">),</span>
|
||||
<span class="lineno">66</span> <span class="n">nn</span><span class="o">.</span><span class="n">ReLU</span><span class="p">(),</span>
|
||||
<span class="lineno">67</span> <span class="p">)</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-6'>
|
||||
@ -175,8 +177,8 @@ frame from third convolution layer, and outputs
|
||||
$512$ features</p>
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">69</span> <span class="bp">self</span><span class="o">.</span><span class="n">lin</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">Linear</span><span class="p">(</span><span class="n">in_features</span><span class="o">=</span><span class="mi">7</span> <span class="o">*</span> <span class="mi">7</span> <span class="o">*</span> <span class="mi">64</span><span class="p">,</span> <span class="n">out_features</span><span class="o">=</span><span class="mi">512</span><span class="p">)</span>
|
||||
<span class="lineno">70</span> <span class="bp">self</span><span class="o">.</span><span class="n">activation</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">ReLU</span><span class="p">()</span></pre></div>
|
||||
<div class="highlight"><pre><span class="lineno">72</span> <span class="bp">self</span><span class="o">.</span><span class="n">lin</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">Linear</span><span class="p">(</span><span class="n">in_features</span><span class="o">=</span><span class="mi">7</span> <span class="o">*</span> <span class="mi">7</span> <span class="o">*</span> <span class="mi">64</span><span class="p">,</span> <span class="n">out_features</span><span class="o">=</span><span class="mi">512</span><span class="p">)</span>
|
||||
<span class="lineno">73</span> <span class="bp">self</span><span class="o">.</span><span class="n">activation</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">ReLU</span><span class="p">()</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-7'>
|
||||
@ -187,11 +189,11 @@ $512$ features</p>
|
||||
<p>This head gives the state value $V$</p>
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">73</span> <span class="bp">self</span><span class="o">.</span><span class="n">state_value</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">Sequential</span><span class="p">(</span>
|
||||
<span class="lineno">74</span> <span class="n">nn</span><span class="o">.</span><span class="n">Linear</span><span class="p">(</span><span class="n">in_features</span><span class="o">=</span><span class="mi">512</span><span class="p">,</span> <span class="n">out_features</span><span class="o">=</span><span class="mi">256</span><span class="p">),</span>
|
||||
<span class="lineno">75</span> <span class="n">nn</span><span class="o">.</span><span class="n">ReLU</span><span class="p">(),</span>
|
||||
<span class="lineno">76</span> <span class="n">nn</span><span class="o">.</span><span class="n">Linear</span><span class="p">(</span><span class="n">in_features</span><span class="o">=</span><span class="mi">256</span><span class="p">,</span> <span class="n">out_features</span><span class="o">=</span><span class="mi">1</span><span class="p">),</span>
|
||||
<span class="lineno">77</span> <span class="p">)</span></pre></div>
|
||||
<div class="highlight"><pre><span class="lineno">76</span> <span class="bp">self</span><span class="o">.</span><span class="n">state_value</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">Sequential</span><span class="p">(</span>
|
||||
<span class="lineno">77</span> <span class="n">nn</span><span class="o">.</span><span class="n">Linear</span><span class="p">(</span><span class="n">in_features</span><span class="o">=</span><span class="mi">512</span><span class="p">,</span> <span class="n">out_features</span><span class="o">=</span><span class="mi">256</span><span class="p">),</span>
|
||||
<span class="lineno">78</span> <span class="n">nn</span><span class="o">.</span><span class="n">ReLU</span><span class="p">(),</span>
|
||||
<span class="lineno">79</span> <span class="n">nn</span><span class="o">.</span><span class="n">Linear</span><span class="p">(</span><span class="n">in_features</span><span class="o">=</span><span class="mi">256</span><span class="p">,</span> <span class="n">out_features</span><span class="o">=</span><span class="mi">1</span><span class="p">),</span>
|
||||
<span class="lineno">80</span> <span class="p">)</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-8'>
|
||||
@ -202,11 +204,11 @@ $512$ features</p>
|
||||
<p>This head gives the action value $A$</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">action_value</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">Sequential</span><span class="p">(</span>
|
||||
<span class="lineno">80</span> <span class="n">nn</span><span class="o">.</span><span class="n">Linear</span><span class="p">(</span><span class="n">in_features</span><span class="o">=</span><span class="mi">512</span><span class="p">,</span> <span class="n">out_features</span><span class="o">=</span><span class="mi">256</span><span class="p">),</span>
|
||||
<span class="lineno">81</span> <span class="n">nn</span><span class="o">.</span><span class="n">ReLU</span><span class="p">(),</span>
|
||||
<span class="lineno">82</span> <span class="n">nn</span><span class="o">.</span><span class="n">Linear</span><span class="p">(</span><span class="n">in_features</span><span class="o">=</span><span class="mi">256</span><span class="p">,</span> <span class="n">out_features</span><span class="o">=</span><span class="mi">4</span><span class="p">),</span>
|
||||
<span class="lineno">83</span> <span class="p">)</span></pre></div>
|
||||
<div class="highlight"><pre><span class="lineno">82</span> <span class="bp">self</span><span class="o">.</span><span class="n">action_value</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">Sequential</span><span class="p">(</span>
|
||||
<span class="lineno">83</span> <span class="n">nn</span><span class="o">.</span><span class="n">Linear</span><span class="p">(</span><span class="n">in_features</span><span class="o">=</span><span class="mi">512</span><span class="p">,</span> <span class="n">out_features</span><span class="o">=</span><span class="mi">256</span><span class="p">),</span>
|
||||
<span class="lineno">84</span> <span class="n">nn</span><span class="o">.</span><span class="n">ReLU</span><span class="p">(),</span>
|
||||
<span class="lineno">85</span> <span class="n">nn</span><span class="o">.</span><span class="n">Linear</span><span class="p">(</span><span class="n">in_features</span><span class="o">=</span><span class="mi">256</span><span class="p">,</span> <span class="n">out_features</span><span class="o">=</span><span class="mi">4</span><span class="p">),</span>
|
||||
<span class="lineno">86</span> <span class="p">)</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-9'>
|
||||
@ -217,7 +219,7 @@ $512$ features</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">85</span> <span class="k">def</span> <span class="nf">forward</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">obs</span><span class="p">:</span> <span class="n">torch</span><span class="o">.</span><span class="n">Tensor</span><span class="p">):</span></pre></div>
|
||||
<div class="highlight"><pre><span class="lineno">88</span> <span class="k">def</span> <span class="nf">forward</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">obs</span><span class="p">:</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-10'>
|
||||
@ -228,7 +230,7 @@ $512$ features</p>
|
||||
<p>Convolution</p>
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">87</span> <span class="n">h</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">conv</span><span class="p">(</span><span class="n">obs</span><span class="p">)</span></pre></div>
|
||||
<div class="highlight"><pre><span class="lineno">90</span> <span class="n">h</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">conv</span><span class="p">(</span><span class="n">obs</span><span class="p">)</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-11'>
|
||||
@ -239,7 +241,7 @@ $512$ features</p>
|
||||
<p>Reshape for linear layers</p>
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">89</span> <span class="n">h</span> <span class="o">=</span> <span class="n">h</span><span class="o">.</span><span class="n">reshape</span><span class="p">((</span><span class="o">-</span><span class="mi">1</span><span class="p">,</span> <span class="mi">7</span> <span class="o">*</span> <span class="mi">7</span> <span class="o">*</span> <span class="mi">64</span><span class="p">))</span></pre></div>
|
||||
<div class="highlight"><pre><span class="lineno">92</span> <span class="n">h</span> <span class="o">=</span> <span class="n">h</span><span class="o">.</span><span class="n">reshape</span><span class="p">((</span><span class="o">-</span><span class="mi">1</span><span class="p">,</span> <span class="mi">7</span> <span class="o">*</span> <span class="mi">7</span> <span class="o">*</span> <span class="mi">64</span><span class="p">))</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-12'>
|
||||
@ -250,7 +252,7 @@ $512$ features</p>
|
||||
<p>Linear layer</p>
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">92</span> <span class="n">h</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">activation</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">lin</span><span class="p">(</span><span class="n">h</span><span class="p">))</span></pre></div>
|
||||
<div class="highlight"><pre><span class="lineno">95</span> <span class="n">h</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">activation</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">lin</span><span class="p">(</span><span class="n">h</span><span class="p">))</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-13'>
|
||||
@ -261,7 +263,7 @@ $512$ features</p>
|
||||
<p>$A$</p>
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">95</span> <span class="n">action_value</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">action_value</span><span class="p">(</span><span class="n">h</span><span class="p">)</span></pre></div>
|
||||
<div class="highlight"><pre><span class="lineno">98</span> <span class="n">action_value</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">action_value</span><span class="p">(</span><span class="n">h</span><span class="p">)</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-14'>
|
||||
@ -272,7 +274,7 @@ $512$ features</p>
|
||||
<p>$V$</p>
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">97</span> <span class="n">state_value</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">state_value</span><span class="p">(</span><span class="n">h</span><span class="p">)</span></pre></div>
|
||||
<div class="highlight"><pre><span class="lineno">100</span> <span class="n">state_value</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">state_value</span><span class="p">(</span><span class="n">h</span><span class="p">)</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-15'>
|
||||
@ -283,7 +285,7 @@ $512$ features</p>
|
||||
<p>$A(s, a) - \frac{1}{|\mathcal{A}|} \sum_{a’ \in \mathcal{A}} A(s, a’)$</p>
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">100</span> <span class="n">action_score_centered</span> <span class="o">=</span> <span class="n">action_value</span> <span class="o">-</span> <span class="n">action_value</span><span class="o">.</span><span class="n">mean</span><span class="p">(</span><span class="n">dim</span><span class="o">=-</span><span class="mi">1</span><span class="p">,</span> <span class="n">keepdim</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span></pre></div>
|
||||
<div class="highlight"><pre><span class="lineno">103</span> <span class="n">action_score_centered</span> <span class="o">=</span> <span class="n">action_value</span> <span class="o">-</span> <span class="n">action_value</span><span class="o">.</span><span class="n">mean</span><span class="p">(</span><span class="n">dim</span><span class="o">=-</span><span class="mi">1</span><span class="p">,</span> <span class="n">keepdim</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-16'>
|
||||
@ -294,9 +296,9 @@ $512$ features</p>
|
||||
<p>$Q(s, a) =V(s) + \Big(A(s, a) - \frac{1}{|\mathcal{A}|} \sum_{a’ \in \mathcal{A}} A(s, a’)\Big)$</p>
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">102</span> <span class="n">q</span> <span class="o">=</span> <span class="n">state_value</span> <span class="o">+</span> <span class="n">action_score_centered</span>
|
||||
<span class="lineno">103</span>
|
||||
<span class="lineno">104</span> <span class="k">return</span> <span class="n">q</span></pre></div>
|
||||
<div class="highlight"><pre><span class="lineno">105</span> <span class="n">q</span> <span class="o">=</span> <span class="n">state_value</span> <span class="o">+</span> <span class="n">action_score_centered</span>
|
||||
<span class="lineno">106</span>
|
||||
<span class="lineno">107</span> <span class="k">return</span> <span class="n">q</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='footer'>
|
||||
|
||||
Reference in New Issue
Block a user