Deploying to gh-pages from @ 6ae1396 🚀

opendilab · Sep 20, 2024 · 3928b3c · 3928b3c
1 parent c1921d9
commit 3928b3c
Showing 1 changed file with 6 additions and 2 deletions.
diff --git a/_modules/ding/model/wrapper/model_wrappers.html b/_modules/ding/model/wrapper/model_wrappers.html
@@ -1170,10 +1170,14 @@ <h1>Source code for ding.model.wrapper.model_wrappers</h1><div class="highlight"
         <span class="k">assert</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">output</span><span class="p">,</span> <span class="nb">dict</span><span class="p">),</span> <span class="s2">&quot;model output must be dict, but find </span><span class="si">{}</span><span class="s2">&quot;</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="nb">type</span><span class="p">(</span><span class="n">output</span><span class="p">))</span>
         <span class="k">if</span> <span class="s1">&#39;action&#39;</span> <span class="ow">in</span> <span class="n">output</span> <span class="ow">or</span> <span class="s1">&#39;action_args&#39;</span> <span class="ow">in</span> <span class="n">output</span><span class="p">:</span>
             <span class="n">key</span> <span class="o">=</span> <span class="s1">&#39;action&#39;</span> <span class="k">if</span> <span class="s1">&#39;action&#39;</span> <span class="ow">in</span> <span class="n">output</span> <span class="k">else</span> <span class="s1">&#39;action_args&#39;</span>
-            <span class="n">action</span> <span class="o">=</span> <span class="n">output</span><span class="p">[</span><span class="n">key</span><span class="p">]</span>
+            <span class="c1"># handle hybrid action space by adding noise to continuous part of model output</span>
+            <span class="n">action</span> <span class="o">=</span> <span class="n">output</span><span class="p">[</span><span class="n">key</span><span class="p">][</span><span class="s1">&#39;action_args&#39;</span><span class="p">]</span> <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">output</span><span class="p">[</span><span class="n">key</span><span class="p">],</span> <span class="nb">dict</span><span class="p">)</span> <span class="k">else</span> <span class="n">output</span><span class="p">[</span><span class="n">key</span><span class="p">]</span>
             <span class="k">assert</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">action</span><span class="p">,</span> <span class="n">torch</span><span class="o">.</span><span class="n">Tensor</span><span class="p">)</span>
             <span class="n">action</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">add_noise</span><span class="p">(</span><span class="n">action</span><span class="p">)</span>
-            <span class="n">output</span><span class="p">[</span><span class="n">key</span><span class="p">]</span> <span class="o">=</span> <span class="n">action</span>
+            <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">output</span><span class="p">[</span><span class="n">key</span><span class="p">],</span> <span class="nb">dict</span><span class="p">):</span>
+                <span class="n">output</span><span class="p">[</span><span class="n">key</span><span class="p">][</span><span class="s1">&#39;action_args&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="n">action</span>
+            <span class="k">else</span><span class="p">:</span>
+                <span class="n">output</span><span class="p">[</span><span class="n">key</span><span class="p">]</span> <span class="o">=</span> <span class="n">action</span>
         <span class="k">return</span> <span class="n">output</span></div>
 
     <span class="k">def</span> <span class="nf">add_noise</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="n">torch</span><span class="o">.</span><span class="n">Tensor</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">torch</span><span class="o">.</span><span class="n">Tensor</span><span class="p">:</span>