Deploying to gh-pages from @ Farama-Foundation/Minigrid@8710e91d2325b5e5e1ce75dae5567fd816298ca7 🚀

main/.buildinfo

@@ -1,4 +1,4 @@
 # Sphinx build info version 1
 # This file hashes the configuration used when building these files. When it is not found, a full rebuild will be done.
-config: e85456c00c15a161776a9b33e8a804fc
+config: cfb421b04e722064c6bedb20f4f636f4
 tags: d77d1c0d9ca2f4c8421862c7c5a0d620

main/_modules/minigrid/wrappers/index.html

@@ -501,7 +501,7 @@
 <a class="viewcode-back" href="../../../api/wrappers/#minigrid.wrappers.PositionBonus">[docs]</a>
 <span class="k">class</span><span class="w"> </span><span class="nc">PositionBonus</span><span class="p">(</span><span class="n">Wrapper</span><span class="p">):</span>
 <span class="w">    </span><span class="sd">&quot;&quot;&quot;</span>
-<span class="sd">    Adds an exploration bonus based on which positions</span>
+<span class="sd">    Adds a scaled exploration bonus based on which positions</span>
 <span class="sd">    are visited on the grid.</span>
 
 <span class="sd">    Note:</span>
@@ -518,7 +518,7 @@
 <span class="sd">        &gt;&gt;&gt; _, reward, _, _, _ = env.step(1)</span>
 <span class="sd">        &gt;&gt;&gt; print(reward)</span>
 <span class="sd">        0</span>
-<span class="sd">        &gt;&gt;&gt; env_bonus = PositionBonus(env)</span>
+<span class="sd">        &gt;&gt;&gt; env_bonus = PositionBonus(env, scale=1)</span>
 <span class="sd">        &gt;&gt;&gt; obs, _ = env_bonus.reset(seed=0)</span>
 <span class="sd">        &gt;&gt;&gt; obs, reward, terminated, truncated, info = env_bonus.step(1)</span>
 <span class="sd">        &gt;&gt;&gt; print(reward)</span>
@@ -528,7 +528,7 @@
 <span class="sd">        0.7071067811865475</span>
 <span class="sd">    &quot;&quot;&quot;</span>
 
-    <span class="k">def</span><span class="w"> </span><span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">env</span><span class="p">):</span>
+    <span class="k">def</span><span class="w"> </span><span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">env</span><span class="p">,</span> <span class="n">scale</span><span class="o">=</span><span class="mi">1</span><span class="p">):</span>
 <span class="w">        </span><span class="sd">&quot;&quot;&quot;A wrapper that adds an exploration bonus to less visited positions.</span>
 
 <span class="sd">        Args:</span>
@@ -536,6 +536,7 @@
 <span class="sd">        &quot;&quot;&quot;</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="n">env</span><span class="p">)</span>
         <span class="bp">self</span><span class="o">.</span><span class="n">counts</span> <span class="o">=</span> <span class="p">{}</span>
+        <span class="bp">self</span><span class="o">.</span><span class="n">scale</span> <span class="o">=</span> <span class="mi">1</span>
 
     <span class="k">def</span><span class="w"> </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>
 <span class="w">        </span><span class="sd">&quot;&quot;&quot;Steps through the environment with `action`.&quot;&quot;&quot;</span>
@@ -547,16 +548,14 @@
         <span class="n">tup</span> <span class="o">=</span> <span class="nb">tuple</span><span class="p">(</span><span class="n">env</span><span class="o">.</span><span class="n">agent_pos</span><span class="p">)</span>
 
         <span class="c1"># Get the count for this key</span>
-        <span class="n">pre_count</span> <span class="o">=</span> <span class="mi">0</span>
-        <span class="k">if</span> <span class="n">tup</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">counts</span><span class="p">:</span>
-            <span class="n">pre_count</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">counts</span><span class="p">[</span><span class="n">tup</span><span class="p">]</span>
+        <span class="n">pre_count</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">counts</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">tup</span><span class="p">,</span> <span class="mi">0</span><span class="p">)</span>
 
         <span class="c1"># Update the count for this key</span>
         <span class="n">new_count</span> <span class="o">=</span> <span class="n">pre_count</span> <span class="o">+</span> <span class="mi">1</span>
         <span class="bp">self</span><span class="o">.</span><span class="n">counts</span><span class="p">[</span><span class="n">tup</span><span class="p">]</span> <span class="o">=</span> <span class="n">new_count</span>
 
         <span class="n">bonus</span> <span class="o">=</span> <span class="mi">1</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">new_count</span><span class="p">)</span>
-        <span class="n">reward</span> <span class="o">+=</span> <span class="n">bonus</span>
+        <span class="n">reward</span> <span class="o">+=</span> <span class="n">bonus</span> <span class="o">*</span> <span class="bp">self</span><span class="o">.</span><span class="n">scale</span>
 
         <span class="k">return</span> <span class="n">obs</span><span class="p">,</span> <span class="n">reward</span><span class="p">,</span> <span class="n">terminated</span><span class="p">,</span> <span class="n">truncated</span><span class="p">,</span> <span class="n">info</span></div>