mirror of
https://github.com/labmlai/annotated_deep_learning_paper_implementations.git
synced 2025-08-16 02:41:38 +08:00
855 lines
49 KiB
HTML
855 lines
49 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 is an annotated implementation/tutorial of CFR on Kuhn Poker"/>
|
|
|
|
<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="CFR on Kuhn Poker"/>
|
|
<meta name="twitter:description" content="This is an annotated implementation/tutorial of CFR on Kuhn Poker"/>
|
|
<meta name="twitter:site" content="@labmlai"/>
|
|
<meta name="twitter:creator" content="@labmlai"/>
|
|
|
|
<meta property="og:url" content="https://nn.labml.ai/cfr/kuhn/index.html"/>
|
|
<meta property="og:title" content="CFR on Kuhn Poker"/>
|
|
<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="CFR on Kuhn Poker"/>
|
|
<meta property="og:description" content="This is an annotated implementation/tutorial of CFR on Kuhn Poker"/>
|
|
|
|
<title>CFR on Kuhn Poker</title>
|
|
<link rel="shortcut icon" href="/icon.png"/>
|
|
<link rel="stylesheet" href="../../pylit.css">
|
|
<link rel="canonical" href="https://nn.labml.ai/cfr/kuhn/index.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">cfr</a>
|
|
<a class="parent" href="index.html">kuhn</a>
|
|
</p>
|
|
<p>
|
|
|
|
<a href="https://github.com/lab-ml/labml_nn/tree/master/labml_nn/cfr/kuhn/__init__.py">
|
|
<img alt="Github"
|
|
src="https://img.shields.io/github/stars/lab-ml/nn?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><a href="../index.html">Counterfactual Regret Minimization (CFR)</a> on Kuhn Poker</h1>
|
|
<p>This applies <a href="../index.html">Counterfactual Regret Minimization (CFR)</a> to Kuhn poker.</p>
|
|
<p><a href="https://en.wikipedia.org/wiki/Kuhn_poker">Kuhn Poker</a> is a two player 3-card betting game.
|
|
The players are dealt one card each out of Ace, King and Queen (no suits).
|
|
There are only three cards in the pack so one card is left out.
|
|
Ace beats King and Queen and King beats Queen - just like in normal ranking of cards.</p>
|
|
<p>Both players ante $1$ chip (blindly bet $1$ chip).
|
|
After looking at the cards, the first player can either pass or bet $1$ chip.
|
|
If first player passes, the the player with higher card wins the pot.
|
|
If first player bets, the second play can bet (i.e. call) $1$ chip or pass (i.e. fold).
|
|
If the second player bets and the player with the higher card wins the pot.
|
|
If the second player passes (i.e. folds) the first player gets the pot.
|
|
This game is played repeatedly and a good strategy will optimize for the long term utility (or winnings).</p>
|
|
<p>Here’s some example games:</p>
|
|
<ul>
|
|
<li><code>KAp</code> - Player 1 gets K. Player 2 gets A. Player 1 passes. Player 2 doesn’t get a betting chance and Player 2 wins the pot of $2$ chips.</li>
|
|
<li><code>QKbp</code> - Player 1 gets Q. Player 2 gets K. Player 1 bets a chip. Player 2 passes (folds). Player 1 gets the pot of $4$ because Player 2 folded.</li>
|
|
<li><code>QAbb</code> - Player 1 gets Q. Player 2 gets A. Player 1 bets a chip. Player 2 also bets (calls). Player 2 wins the pot of $4$.</li>
|
|
</ul>
|
|
<p>He we extend the <code>InfoSet</code> class and <code>History</code> class defined in <a href="../index.html"><code>__init__.py</code></a>
|
|
with Kuhn Poker specifics.</p>
|
|
<p><a href="https://colab.research.google.com/github/lab-ml/nn/blob/master/labml_nn/cfr/kuhn/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/7c35d3fad29711eba588acde48001122"><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">38</span><span></span><span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">List</span><span class="p">,</span> <span class="n">cast</span><span class="p">,</span> <span class="n">Dict</span>
|
|
<span class="lineno">39</span>
|
|
<span class="lineno">40</span><span class="kn">import</span> <span class="nn">numpy</span> <span class="k">as</span> <span class="nn">np</span>
|
|
<span class="lineno">41</span>
|
|
<span class="lineno">42</span><span class="kn">from</span> <span class="nn">labml</span> <span class="kn">import</span> <span class="n">experiment</span>
|
|
<span class="lineno">43</span><span class="kn">from</span> <span class="nn">labml.configs</span> <span class="kn">import</span> <span class="n">option</span>
|
|
<span class="lineno">44</span><span class="kn">from</span> <span class="nn">labml_nn.cfr</span> <span class="kn">import</span> <span class="n">History</span> <span class="k">as</span> <span class="n">_History</span><span class="p">,</span> <span class="n">InfoSet</span> <span class="k">as</span> <span class="n">_InfoSet</span><span class="p">,</span> <span class="n">Action</span><span class="p">,</span> <span class="n">Player</span><span class="p">,</span> <span class="n">CFRConfigs</span>
|
|
<span class="lineno">45</span><span class="kn">from</span> <span class="nn">labml_nn.cfr.infoset_saver</span> <span class="kn">import</span> <span class="n">InfoSetSaver</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>Kuhn poker actions are pass (<code>p</code>) or bet (<code>b</code>)</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">48</span><span class="n">ACTIONS</span> <span class="o">=</span> <span class="n">cast</span><span class="p">(</span><span class="n">List</span><span class="p">[</span><span class="n">Action</span><span class="p">],</span> <span class="p">[</span><span class="s1">'p'</span><span class="p">,</span> <span class="s1">'b'</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>
|
|
<p>The three cards in play are Ace, King and Queen</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">50</span><span class="n">CHANCES</span> <span class="o">=</span> <span class="n">cast</span><span class="p">(</span><span class="n">List</span><span class="p">[</span><span class="n">Action</span><span class="p">],</span> <span class="p">[</span><span class="s1">'A'</span><span class="p">,</span> <span class="s1">'K'</span><span class="p">,</span> <span class="s1">'Q'</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>There are two players</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">52</span><span class="n">PLAYERS</span> <span class="o">=</span> <span class="n">cast</span><span class="p">(</span><span class="n">List</span><span class="p">[</span><span class="n">Player</span><span class="p">],</span> <span class="p">[</span><span class="mi">0</span><span class="p">,</span> <span class="mi">1</span><span class="p">])</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><a href="../index.html#InfoSet">Information set</a></h2>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">55</span><span class="k">class</span> <span class="nc">InfoSet</span><span class="p">(</span><span class="n">_InfoSet</span><span class="p">):</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-5'>
|
|
<div class='docs doc-strings'>
|
|
<div class='section-link'>
|
|
<a href='#section-5'>#</a>
|
|
</div>
|
|
<p>Does not support save/load</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">60</span> <span class="nd">@staticmethod</span>
|
|
<span class="lineno">61</span> <span class="k">def</span> <span class="nf">from_dict</span><span class="p">(</span><span class="n">data</span><span class="p">:</span> <span class="n">Dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="nb">any</span><span class="p">])</span> <span class="o">-></span> <span class="s1">'InfoSet'</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>
|
|
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">63</span> <span class="k">pass</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-7'>
|
|
<div class='docs doc-strings'>
|
|
<div class='section-link'>
|
|
<a href='#section-7'>#</a>
|
|
</div>
|
|
<p>Return the list of actions. Terminal states are handled by <code>History</code> class.</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">65</span> <span class="k">def</span> <span class="nf">actions</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="n">List</span><span class="p">[</span><span class="n">Action</span><span class="p">]:</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-8'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-8'>#</a>
|
|
</div>
|
|
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">69</span> <span class="k">return</span> <span class="n">ACTIONS</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-9'>
|
|
<div class='docs doc-strings'>
|
|
<div class='section-link'>
|
|
<a href='#section-9'>#</a>
|
|
</div>
|
|
<p>Human readable string representation - it gives the betting probability</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">71</span> <span class="k">def</span> <span class="fm">__repr__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-10'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-10'>#</a>
|
|
</div>
|
|
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">75</span> <span class="n">total</span> <span class="o">=</span> <span class="nb">sum</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">cumulative_strategy</span><span class="o">.</span><span class="n">values</span><span class="p">())</span>
|
|
<span class="lineno">76</span> <span class="n">total</span> <span class="o">=</span> <span class="nb">max</span><span class="p">(</span><span class="n">total</span><span class="p">,</span> <span class="mf">1e-6</span><span class="p">)</span>
|
|
<span class="lineno">77</span> <span class="n">bet</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">cumulative_strategy</span><span class="p">[</span><span class="n">cast</span><span class="p">(</span><span class="n">Action</span><span class="p">,</span> <span class="s1">'b'</span><span class="p">)]</span> <span class="o">/</span> <span class="n">total</span>
|
|
<span class="lineno">78</span> <span class="k">return</span> <span class="sa">f</span><span class="s1">'</span><span class="si">{</span><span class="n">bet</span> <span class="o">*</span> <span class="mi">100</span><span class="si">:</span><span class="s1"> .1f</span><span class="si">}</span><span class="s1">%'</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-11'>
|
|
<div class='docs doc-strings'>
|
|
<div class='section-link'>
|
|
<a href='#section-11'>#</a>
|
|
</div>
|
|
<h2><a href="../index.html#History">History</a></h2>
|
|
<p>This defines when a game ends, calculates the utility and sample chance events (dealing cards).</p>
|
|
<p>The history is stored in a string:
|
|
* First two characters are the cards dealt to player 1 and player 2
|
|
* The third character is the action by the first player
|
|
* Fourth character is the action by the second player</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">81</span><span class="k">class</span> <span class="nc">History</span><span class="p">(</span><span class="n">_History</span><span class="p">):</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>History</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">94</span> <span class="n">history</span><span class="p">:</span> <span class="nb">str</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-13'>
|
|
<div class='docs doc-strings'>
|
|
<div class='section-link'>
|
|
<a href='#section-13'>#</a>
|
|
</div>
|
|
<p>Initialize with a given history string</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">96</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">history</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s1">''</span><span class="p">):</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-14'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-14'>#</a>
|
|
</div>
|
|
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">100</span> <span class="bp">self</span><span class="o">.</span><span class="n">history</span> <span class="o">=</span> <span class="n">history</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-15'>
|
|
<div class='docs doc-strings'>
|
|
<div class='section-link'>
|
|
<a href='#section-15'>#</a>
|
|
</div>
|
|
<p>Whether the history is terminal (game over).</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">102</span> <span class="k">def</span> <span class="nf">is_terminal</span><span class="p">(</span><span class="bp">self</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>Players are yet to take actions</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">107</span> <span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">history</span><span class="p">)</span> <span class="o"><=</span> <span class="mi">2</span><span class="p">:</span>
|
|
<span class="lineno">108</span> <span class="k">return</span> <span class="kc">False</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>Last player to play passed (game over)</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">110</span> <span class="k">elif</span> <span class="bp">self</span><span class="o">.</span><span class="n">history</span><span class="p">[</span><span class="o">-</span><span class="mi">1</span><span class="p">]</span> <span class="o">==</span> <span class="s1">'p'</span><span class="p">:</span>
|
|
<span class="lineno">111</span> <span class="k">return</span> <span class="kc">True</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>Both players called (bet) (game over)</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">113</span> <span class="k">elif</span> <span class="bp">self</span><span class="o">.</span><span class="n">history</span><span class="p">[</span><span class="o">-</span><span class="mi">2</span><span class="p">:]</span> <span class="o">==</span> <span class="s1">'bb'</span><span class="p">:</span>
|
|
<span class="lineno">114</span> <span class="k">return</span> <span class="kc">True</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>Any other combination</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">116</span> <span class="k">else</span><span class="p">:</span>
|
|
<span class="lineno">117</span> <span class="k">return</span> <span class="kc">False</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-20'>
|
|
<div class='docs doc-strings'>
|
|
<div class='section-link'>
|
|
<a href='#section-20'>#</a>
|
|
</div>
|
|
<p>Calculate the terminal utility for player $1$, $u_1(z)$</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">119</span> <span class="k">def</span> <span class="nf">_terminal_utility_p1</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="nb">float</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>$+1$ if Player 1 has a better card and $-1$ otherwise</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">124</span> <span class="n">winner</span> <span class="o">=</span> <span class="o">-</span><span class="mi">1</span> <span class="o">+</span> <span class="mi">2</span> <span class="o">*</span> <span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">history</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="o"><</span> <span class="bp">self</span><span class="o">.</span><span class="n">history</span><span class="p">[</span><span class="mi">1</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>
|
|
<p>Second player passed</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">127</span> <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">history</span><span class="p">[</span><span class="o">-</span><span class="mi">2</span><span class="p">:]</span> <span class="o">==</span> <span class="s1">'bp'</span><span class="p">:</span>
|
|
<span class="lineno">128</span> <span class="k">return</span> <span class="mi">1</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>Both players called, the player with better card wins $2$ chips</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">130</span> <span class="k">elif</span> <span class="bp">self</span><span class="o">.</span><span class="n">history</span><span class="p">[</span><span class="o">-</span><span class="mi">2</span><span class="p">:]</span> <span class="o">==</span> <span class="s1">'bb'</span><span class="p">:</span>
|
|
<span class="lineno">131</span> <span class="k">return</span> <span class="n">winner</span> <span class="o">*</span> <span class="mi">2</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>First player passed, the player with better card wins $1$ chip</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">133</span> <span class="k">elif</span> <span class="bp">self</span><span class="o">.</span><span class="n">history</span><span class="p">[</span><span class="o">-</span><span class="mi">1</span><span class="p">]</span> <span class="o">==</span> <span class="s1">'p'</span><span class="p">:</span>
|
|
<span class="lineno">134</span> <span class="k">return</span> <span class="n">winner</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>History is non-terminal</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">136</span> <span class="k">else</span><span class="p">:</span>
|
|
<span class="lineno">137</span> <span class="k">raise</span> <span class="ne">RuntimeError</span><span class="p">()</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>Get the terminal utility for player $i$</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">139</span> <span class="k">def</span> <span class="nf">terminal_utility</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">i</span><span class="p">:</span> <span class="n">Player</span><span class="p">)</span> <span class="o">-></span> <span class="nb">float</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>
|
|
<p>If $i$ is Player 1</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">144</span> <span class="k">if</span> <span class="n">i</span> <span class="o">==</span> <span class="n">PLAYERS</span><span class="p">[</span><span class="mi">0</span><span class="p">]:</span>
|
|
<span class="lineno">145</span> <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_terminal_utility_p1</span><span class="p">()</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-28'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-28'>#</a>
|
|
</div>
|
|
<p>Otherwise, $u_2(z) = -u_1(z)$</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">147</span> <span class="k">else</span><span class="p">:</span>
|
|
<span class="lineno">148</span> <span class="k">return</span> <span class="o">-</span><span class="mi">1</span> <span class="o">*</span> <span class="bp">self</span><span class="o">.</span><span class="n">_terminal_utility_p1</span><span class="p">()</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-29'>
|
|
<div class='docs doc-strings'>
|
|
<div class='section-link'>
|
|
<a href='#section-29'>#</a>
|
|
</div>
|
|
<p>The first two events are card dealing; i.e. chance events</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">150</span> <span class="k">def</span> <span class="nf">is_chance</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="nb">bool</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>
|
|
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">154</span> <span class="k">return</span> <span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">history</span><span class="p">)</span> <span class="o"><</span> <span class="mi">2</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-31'>
|
|
<div class='docs doc-strings'>
|
|
<div class='section-link'>
|
|
<a href='#section-31'>#</a>
|
|
</div>
|
|
<p>Add an action to the history and return a new history</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">156</span> <span class="k">def</span> <span class="fm">__add__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">other</span><span class="p">:</span> <span class="n">Action</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>
|
|
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">160</span> <span class="k">return</span> <span class="n">History</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">history</span> <span class="o">+</span> <span class="n">other</span><span class="p">)</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-33'>
|
|
<div class='docs doc-strings'>
|
|
<div class='section-link'>
|
|
<a href='#section-33'>#</a>
|
|
</div>
|
|
<p>Current player</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">162</span> <span class="k">def</span> <span class="nf">player</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="n">Player</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>
|
|
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">166</span> <span class="k">return</span> <span class="n">cast</span><span class="p">(</span><span class="n">Player</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">history</span><span class="p">)</span> <span class="o">%</span> <span class="mi">2</span><span class="p">)</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-35'>
|
|
<div class='docs doc-strings'>
|
|
<div class='section-link'>
|
|
<a href='#section-35'>#</a>
|
|
</div>
|
|
<p>Sample a chance action</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">168</span> <span class="k">def</span> <span class="nf">sample_chance</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="n">Action</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>
|
|
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">172</span> <span class="k">while</span> <span class="kc">True</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>Randomly pick a card</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">174</span> <span class="n">r</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">randint</span><span class="p">(</span><span class="nb">len</span><span class="p">(</span><span class="n">CHANCES</span><span class="p">))</span>
|
|
<span class="lineno">175</span> <span class="n">chance</span> <span class="o">=</span> <span class="n">CHANCES</span><span class="p">[</span><span class="n">r</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>See if the card was dealt before</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">177</span> <span class="k">for</span> <span class="n">c</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">history</span><span class="p">:</span>
|
|
<span class="lineno">178</span> <span class="k">if</span> <span class="n">c</span> <span class="o">==</span> <span class="n">chance</span><span class="p">:</span>
|
|
<span class="lineno">179</span> <span class="n">chance</span> <span class="o">=</span> <span class="kc">None</span>
|
|
<span class="lineno">180</span> <span class="k">break</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-39'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-39'>#</a>
|
|
</div>
|
|
<p>Return the card if it was not dealt before</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">183</span> <span class="k">if</span> <span class="n">chance</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
|
|
<span class="lineno">184</span> <span class="k">return</span> <span class="n">cast</span><span class="p">(</span><span class="n">Action</span><span class="p">,</span> <span class="n">chance</span><span class="p">)</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-40'>
|
|
<div class='docs doc-strings'>
|
|
<div class='section-link'>
|
|
<a href='#section-40'>#</a>
|
|
</div>
|
|
<p>Human readable representation</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">186</span> <span class="k">def</span> <span class="fm">__repr__</span><span class="p">(</span><span class="bp">self</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>
|
|
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">190</span> <span class="k">return</span> <span class="nb">repr</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">history</span><span class="p">)</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-42'>
|
|
<div class='docs doc-strings'>
|
|
<div class='section-link'>
|
|
<a href='#section-42'>#</a>
|
|
</div>
|
|
<p>Information set key for the current history.
|
|
This is a string of actions only visible to the current player.</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">192</span> <span class="k">def</span> <span class="nf">info_set_key</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="nb">str</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 current player</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">198</span> <span class="n">i</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">player</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>Current player sees her card and the betting actions</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">200</span> <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">history</span><span class="p">[</span><span class="n">i</span><span class="p">]</span> <span class="o">+</span> <span class="bp">self</span><span class="o">.</span><span class="n">history</span><span class="p">[</span><span class="mi">2</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>
|
|
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">202</span> <span class="k">def</span> <span class="nf">new_info_set</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="n">InfoSet</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>Create a new information set object</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">204</span> <span class="k">return</span> <span class="n">InfoSet</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">info_set_key</span><span class="p">())</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-47'>
|
|
<div class='docs doc-strings'>
|
|
<div class='section-link'>
|
|
<a href='#section-47'>#</a>
|
|
</div>
|
|
<p>A function to create an empty history object</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">207</span><span class="k">def</span> <span class="nf">create_new_history</span><span class="p">():</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-48'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-48'>#</a>
|
|
</div>
|
|
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">209</span> <span class="k">return</span> <span class="n">History</span><span class="p">()</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-49'>
|
|
<div class='docs doc-strings'>
|
|
<div class='section-link'>
|
|
<a href='#section-49'>#</a>
|
|
</div>
|
|
<p>Configurations extends the CFR configurations class</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">212</span><span class="k">class</span> <span class="nc">Configs</span><span class="p">(</span><span class="n">CFRConfigs</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>
|
|
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">216</span> <span class="k">pass</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-51'>
|
|
<div class='docs doc-strings'>
|
|
<div class='section-link'>
|
|
<a href='#section-51'>#</a>
|
|
</div>
|
|
<p>Set the <code>create_new_history</code> method for Kuhn Poker</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">219</span><span class="nd">@option</span><span class="p">(</span><span class="n">Configs</span><span class="o">.</span><span class="n">create_new_history</span><span class="p">)</span>
|
|
<span class="lineno">220</span><span class="k">def</span> <span class="nf">_cnh</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>
|
|
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">224</span> <span class="k">return</span> <span class="n">create_new_history</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 the experiment</h3>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">227</span><span class="k">def</span> <span class="nf">main</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>Create an experiment, we only write tracking information to <code>sqlite</code> to speed things up.
|
|
Since the algorithm iterates fast and we track data on each iteration, writing to
|
|
other destinations such as Tensorboard can be relatively time consuming.
|
|
SQLite is enough for our analytics.</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">236</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">'kuhn_poker'</span><span class="p">,</span> <span class="n">writers</span><span class="o">=</span><span class="p">{</span><span class="s1">'sqlite'</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>Initialize configuration</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">238</span> <span class="n">conf</span> <span class="o">=</span> <span class="n">Configs</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>Load configuration</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">configs</span><span class="p">(</span><span class="n">conf</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>Set models for saving</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">242</span> <span class="n">experiment</span><span class="o">.</span><span class="n">add_model_savers</span><span class="p">({</span><span class="s1">'info_sets'</span><span class="p">:</span> <span class="n">InfoSetSaver</span><span class="p">(</span><span class="n">conf</span><span class="o">.</span><span class="n">cfr</span><span class="o">.</span><span class="n">info_sets</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>Start 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></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 iterating</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">246</span> <span class="n">conf</span><span class="o">.</span><span class="n">cfr</span><span class="o">.</span><span class="n">iterate</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>
|
|
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">250</span><span class="k">if</span> <span class="vm">__name__</span> <span class="o">==</span> <span class="s1">'__main__'</span><span class="p">:</span>
|
|
<span class="lineno">251</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>
|
|
<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> |