Prise3D
/
Thesis-OptimizationModules


			
							123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341
							

<!DOCTYPE html>
<!--[if IE 8]><html class="no-js lt-ie9" lang="en" > <![endif]-->
<!--[if gt IE 8]><!--> <html class="no-js" lang="en" > <!--<![endif]-->
<head>
  <meta charset="utf-8">
  
  <meta name="viewport" content="width=device-width, initial-scale=1.0">
  
  <title>macop.policies.reinforcement &mdash; macop v1.0.5 documentation</title>
  

  <script type="text/javascript" src="../../../_static/js/modernizr.min.js"></script>
  
    
      <script type="text/javascript" id="documentation_options" data-url_root="../../../" src="../../../_static/documentation_options.js"></script>
        <script type="text/javascript" src="../../../_static/jquery.js"></script>
        <script type="text/javascript" src="../../../_static/underscore.js"></script>
        <script type="text/javascript" src="../../../_static/doctools.js"></script>
        <script type="text/javascript" src="../../../_static/language_data.js"></script>
    
    <script type="text/javascript" src="../../../_static/js/theme.js"></script>

    
  <link rel="stylesheet" href="../../../_static/css/theme.css" type="text/css" />
  <link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" />
  <link rel="stylesheet" href="../../../_static/css/custom.css" type="text/css" />
    <link rel="index" title="Index" href="../../../genindex.html" />
    <link rel="search" title="Search" href="../../../search.html" /> 
</head>

<body class="wy-body-for-nav">

   
  <div class="wy-grid-for-nav">
    
    <nav data-toggle="wy-nav-shift" class="wy-nav-side">
      <div class="wy-side-scroll">
        <div class="wy-side-nav-search" >
          

            <a href="../../../index.html" class="icon icon-home"> macop
          

          </a>

          
              <div class="version">
                1.0.5
              </div>
            
          
<div role="search">
  <form id="rtd-search-form" class="wy-form" action="../../../search.html" method="get">
    <input type="text" name="q" placeholder="Search docs" />
    <input type="hidden" name="check_keywords" value="yes" />
    <input type="hidden" name="area" value="default" />
  </form>
</div>

          
        </div>

        <div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="main navigation">
          
            
              <p class="caption"><span class="caption-text">Contents:</span></p>
<ul>
<li class="toctree-l1"><a class="reference internal" href="../../../description.html">Description</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../api.html">API</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../documentations/index.html">Documentation</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../examples.html">Some examples</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../contributing.html">Contributing</a></li>
</ul>

            
        </div>
      </div>
    </nav>

    <section data-toggle="wy-nav-shift" class="wy-nav-content-wrap">

      
      <nav class="wy-nav-top" aria-label="top navigation">
        
          <i data-toggle="wy-nav-top" class="fa fa-bars"></i>
          <a href="../../../index.html">macop</a>
        
      </nav>


      <div class="wy-nav-content">
        
        <div class="rst-content">
        
          
<div role="navigation" aria-label="breadcrumbs navigation">

  <ul class="wy-breadcrumbs">
    
      <li><a href="../../../index.html">Docs</a> &raquo;</li>
        
          <li><a href="../../index.html">Module code</a> &raquo;</li>
        
      <li>macop.policies.reinforcement</li>
    
    
      <li class="wy-breadcrumbs-aside">
        
      </li>
    
  </ul>

  
  <hr/>
</div>
          <div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article">
           <div itemprop="articleBody">
            
  <h1>Source code for macop.policies.reinforcement</h1><div class="highlight"><pre>
<span></span><span class="sd">&quot;&quot;&quot;Reinforcement learning policy classes implementations for Operator Selection Strategy</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="c1"># main imports</span>
<span class="kn">import</span> <span class="nn">logging</span>
<span class="kn">import</span> <span class="nn">random</span>
<span class="kn">import</span> <span class="nn">math</span>
<span class="kn">import</span> <span class="nn">numpy</span> <span class="k">as</span> <span class="nn">np</span>

<span class="c1"># module imports</span>
<span class="kn">from</span> <span class="nn">.base</span> <span class="kn">import</span> <span class="n">Policy</span>


<div class="viewcode-block" id="UCBPolicy"><a class="viewcode-back" href="../../../macop/macop.policies.reinforcement.html#macop.policies.reinforcement.UCBPolicy">[docs]</a><span class="k">class</span> <span class="nc">UCBPolicy</span><span class="p">(</span><span class="n">Policy</span><span class="p">):</span>
    <span class="sd">&quot;&quot;&quot;Upper Confidence Bound (UCB) policy class which is used for applying UCB strategy when selecting and applying operator</span>

<span class="sd">    Rather than performing exploration by simply selecting an arbitrary action, chosen with a probability that remains constant,</span>
<span class="sd">    the UCB algorithm changes its exploration-exploitation balance as it gathers more knowledge of the environment.</span>
<span class="sd">    It moves from being primarily focused on exploration, when actions that have been tried the least are preferred,</span>
<span class="sd">    to instead concentrate on exploitation, selecting the action with the highest estimated reward.</span>

<span class="sd">    - Resource link: https://banditalgs.com/2016/09/18/the-upper-confidence-bound-algorithm/</span>

<span class="sd">    Attributes:</span>
<span class="sd">        operators: {[Operator]} -- list of selected operators for the algorithm</span>
<span class="sd">        C: {float} -- The second half of the UCB equation adds exploration, with the degree of exploration being controlled by the hyper-parameter `C`.</span>
<span class="sd">        exp_rate: {float} -- exploration rate (probability to choose randomly next operator)</span>
<span class="sd">        rewards: {[float]} -- list of summed rewards obtained for each operator</span>
<span class="sd">        occurrences: {[int]} -- number of use (selected) of each operator</span>

<span class="sd">    Example:</span>

<span class="sd">    &gt;&gt;&gt; # operators import</span>
<span class="sd">    &gt;&gt;&gt; from macop.operators.discrete.crossovers import SimpleCrossover</span>
<span class="sd">    &gt;&gt;&gt; from macop.operators.discrete.mutators import SimpleMutation</span>
<span class="sd">    &gt;&gt;&gt; # policy import</span>
<span class="sd">    &gt;&gt;&gt; from macop.policies.reinforcement import UCBPolicy</span>
<span class="sd">    &gt;&gt;&gt; # solution and algorithm</span>
<span class="sd">    &gt;&gt;&gt; from macop.solutions.discrete import BinarySolution</span>
<span class="sd">    &gt;&gt;&gt; from macop.algorithms.mono import IteratedLocalSearch</span>
<span class="sd">    &gt;&gt;&gt; # evaluator import</span>
<span class="sd">    &gt;&gt;&gt; from macop.evaluators.discrete.mono import KnapsackEvaluator</span>
<span class="sd">    &gt;&gt;&gt; # evaluator initialization (worths objects passed into data)</span>
<span class="sd">    &gt;&gt;&gt; worths = [ random.randint(0, 20) for i in range(20) ]</span>
<span class="sd">    &gt;&gt;&gt; evaluator = KnapsackEvaluator(data={&#39;worths&#39;: worths})</span>
<span class="sd">    &gt;&gt;&gt; # validator specification (based on weights of each objects)</span>
<span class="sd">    &gt;&gt;&gt; weights = [ random.randint(5, 30) for i in range(20) ]</span>
<span class="sd">    &gt;&gt;&gt; validator = lambda solution: True if sum([weights[i] for i, value in enumerate(solution._data) if value == 1]) &lt; 200 else False</span>
<span class="sd">    &gt;&gt;&gt; # initializer function with lambda function</span>
<span class="sd">    &gt;&gt;&gt; initializer = lambda x=20: BinarySolution.random(x, validator)</span>
<span class="sd">    &gt;&gt;&gt; # operators list with crossover and mutation</span>
<span class="sd">    &gt;&gt;&gt; operators = [SimpleCrossover(), SimpleMutation()]</span>
<span class="sd">    &gt;&gt;&gt; policy = UCBPolicy(operators)</span>
<span class="sd">    &gt;&gt;&gt; algo = IteratedLocalSearch(initializer, evaluator, operators, policy, validator, maximise=True, verbose=False)</span>
<span class="sd">    &gt;&gt;&gt; policy._occurences</span>
<span class="sd">    [0, 0]</span>
<span class="sd">    &gt;&gt;&gt; solution = algo.run(100)</span>
<span class="sd">    &gt;&gt;&gt; type(solution).__name__</span>
<span class="sd">    &#39;BinarySolution&#39;</span>
<span class="sd">    &gt;&gt;&gt; policy._occurences # one more due to first evaluation</span>
<span class="sd">    [51, 53]</span>
<span class="sd">    &quot;&quot;&quot;</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">operators</span><span class="p">,</span> <span class="n">C</span><span class="o">=</span><span class="mf">100.</span><span class="p">,</span> <span class="n">exp_rate</span><span class="o">=</span><span class="mf">0.5</span><span class="p">):</span>
        <span class="bp">self</span><span class="o">.</span><span class="n">_operators</span> <span class="o">=</span> <span class="n">operators</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="mf">0.</span> <span class="k">for</span> <span class="n">o</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_operators</span><span class="p">]</span>
        <span class="bp">self</span><span class="o">.</span><span class="n">_occurences</span> <span class="o">=</span> <span class="p">[</span><span class="mi">0</span> <span class="k">for</span> <span class="n">o</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_operators</span><span class="p">]</span>
        <span class="bp">self</span><span class="o">.</span><span class="n">_C</span> <span class="o">=</span> <span class="n">C</span>
        <span class="bp">self</span><span class="o">.</span><span class="n">_exp_rate</span> <span class="o">=</span> <span class="n">exp_rate</span>


<div class="viewcode-block" id="UCBPolicy.select"><a class="viewcode-back" href="../../../macop/macop.policies.reinforcement.html#macop.policies.reinforcement.UCBPolicy.select">[docs]</a>    <span class="k">def</span> <span class="nf">select</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
        <span class="sd">&quot;&quot;&quot;Select using Upper Confidence Bound the next operator to use (using acquired rewards)</span>

<span class="sd">        Returns:</span>
<span class="sd">            {Operator}: the selected operator</span>
<span class="sd">        &quot;&quot;&quot;</span>

        <span class="n">indices</span> <span class="o">=</span> <span class="p">[</span><span class="n">i</span> <span class="k">for</span> <span class="n">i</span><span class="p">,</span> <span class="n">o</span> <span class="ow">in</span> <span class="nb">enumerate</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_occurences</span><span class="p">)</span> <span class="k">if</span> <span class="n">o</span> <span class="o">==</span> <span class="mi">0</span><span class="p">]</span>

        <span class="c1"># random choice following exploration rate</span>
        <span class="k">if</span> <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">uniform</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="mi">1</span><span class="p">)</span> <span class="o">&lt;=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_exp_rate</span><span class="p">:</span>

            <span class="n">index</span> <span class="o">=</span> <span class="n">random</span><span class="o">.</span><span class="n">choice</span><span class="p">(</span><span class="nb">range</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">_operators</span><span class="p">)))</span>
            <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_operators</span><span class="p">[</span><span class="n">index</span><span class="p">]</span>

        <span class="k">elif</span> <span class="nb">len</span><span class="p">(</span><span class="n">indices</span><span class="p">)</span> <span class="o">==</span> <span class="mi">0</span><span class="p">:</span>

            <span class="c1"># if operator have at least be used one time</span>
            <span class="n">ucbValues</span> <span class="o">=</span> <span class="p">[]</span>
            <span class="n">nVisits</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">_occurences</span><span class="p">)</span>

            <span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_operators</span><span class="p">)):</span>

                <span class="n">ucbValue</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_rewards</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">_C</span> <span class="o">*</span> <span class="n">math</span><span class="o">.</span><span class="n">sqrt</span><span class="p">(</span>
                    <span class="n">math</span><span class="o">.</span><span class="n">log</span><span class="p">(</span><span class="n">nVisits</span><span class="p">)</span> <span class="o">/</span> <span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_occurences</span><span class="p">[</span><span class="n">i</span><span class="p">]</span> <span class="o">+</span> <span class="mf">0.1</span><span class="p">))</span>
                <span class="n">ucbValues</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">ucbValue</span><span class="p">)</span>

            <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_operators</span><span class="p">[</span><span class="n">ucbValues</span><span class="o">.</span><span class="n">index</span><span class="p">(</span><span class="nb">max</span><span class="p">(</span><span class="n">ucbValues</span><span class="p">))]</span>

        <span class="k">else</span><span class="p">:</span>
            <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_operators</span><span class="p">[</span><span class="n">random</span><span class="o">.</span><span class="n">choice</span><span class="p">(</span><span class="n">indices</span><span class="p">)]</span></div>

<div class="viewcode-block" id="UCBPolicy.apply"><a class="viewcode-back" href="../../../macop/macop.policies.reinforcement.html#macop.policies.reinforcement.UCBPolicy.apply">[docs]</a>    <span class="k">def</span> <span class="nf">apply</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">solution</span><span class="p">):</span>
        <span class="sd">&quot;&quot;&quot;</span>
<span class="sd">        Apply specific operator chosen to create new solution, computes its fitness and returns solution</span>

<span class="sd">        - fitness improvment is saved as rewards</span>
<span class="sd">        - selected operator occurence is also increased</span>

<span class="sd">        Args:</span>
<span class="sd">            solution: {Solution} -- the solution to use for generating new solution</span>

<span class="sd">        Returns:</span>
<span class="sd">            {Solution} -- new generated solution</span>
<span class="sd">        &quot;&quot;&quot;</span>

        <span class="n">operator</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">select</span><span class="p">()</span>

        <span class="n">logging</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s2">&quot;---- Applying </span><span class="si">%s</span><span class="s2"> on </span><span class="si">%s</span><span class="s2">&quot;</span> <span class="o">%</span>
                     <span class="p">(</span><span class="nb">type</span><span class="p">(</span><span class="n">operator</span><span class="p">)</span><span class="o">.</span><span class="vm">__name__</span><span class="p">,</span> <span class="n">solution</span><span class="p">))</span>

        <span class="c1"># apply operator on solution</span>
        <span class="n">newSolution</span> <span class="o">=</span> <span class="n">operator</span><span class="o">.</span><span class="n">apply</span><span class="p">(</span><span class="n">solution</span><span class="p">)</span>

        <span class="c1"># compute fitness of new solution</span>
        <span class="n">newSolution</span><span class="o">.</span><span class="n">evaluate</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_algo</span><span class="o">.</span><span class="n">_evaluator</span><span class="p">)</span>

        <span class="c1"># compute fitness improvment rate</span>
        <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_algo</span><span class="o">.</span><span class="n">_maximise</span><span class="p">:</span>
            <span class="n">fir</span> <span class="o">=</span> <span class="p">(</span><span class="n">newSolution</span><span class="o">.</span><span class="n">fitness</span><span class="p">()</span> <span class="o">-</span>
                   <span class="n">solution</span><span class="o">.</span><span class="n">fitness</span><span class="p">())</span> <span class="o">/</span> <span class="n">solution</span><span class="o">.</span><span class="n">fitness</span><span class="p">()</span>
        <span class="k">else</span><span class="p">:</span>
            <span class="n">fir</span> <span class="o">=</span> <span class="p">(</span><span class="n">solution</span><span class="o">.</span><span class="n">fitness</span><span class="p">()</span> <span class="o">-</span>
                   <span class="n">newSolution</span><span class="o">.</span><span class="n">fitness</span><span class="p">())</span> <span class="o">/</span> <span class="n">solution</span><span class="o">.</span><span class="n">fitness</span><span class="p">()</span>

        <span class="n">operator_index</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_operators</span><span class="o">.</span><span class="n">index</span><span class="p">(</span><span class="n">operator</span><span class="p">)</span>

        <span class="k">if</span> <span class="n">fir</span> <span class="o">&gt;</span> <span class="mi">0</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="n">operator_index</span><span class="p">]</span> <span class="o">+=</span> <span class="n">fir</span>

        <span class="bp">self</span><span class="o">.</span><span class="n">_occurences</span><span class="p">[</span><span class="n">operator_index</span><span class="p">]</span> <span class="o">+=</span> <span class="mi">1</span>

        <span class="n">logging</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s2">&quot;---- Obtaining </span><span class="si">%s</span><span class="s2">&quot;</span> <span class="o">%</span> <span class="p">(</span><span class="n">solution</span><span class="p">))</span>

        <span class="k">return</span> <span class="n">newSolution</span></div></div>
</pre></div>

           </div>
           
          </div>
          <footer>
  

  <hr/>

  <div role="contentinfo">
    <p>
        &copy; Copyright 2020, Jérôme BUISINE

    </p>
  </div>
  Built with <a href="http://sphinx-doc.org/">Sphinx</a> using a <a href="https://github.com/rtfd/sphinx_rtd_theme">theme</a> provided by <a href="https://readthedocs.org">Read the Docs</a>. 

</footer>

        </div>
      </div>

    </section>

  </div>
  

  <script type="text/javascript">
      jQuery(function () {
          SphinxRtdTheme.Navigation.enable(true);
      });
  </script>

  
</body>
</html>