Deploying to gh-pages from @ 414b5305 🚀

_modules/ding/worker/collector/base_serial_evaluator.html

@@ -316,6 +316,8 @@
 <span class="sd">            Determine whether you need to start the evaluation mode, if the number of training has reached\</span>
 <span class="sd">                the maximum number of times to start the evaluator, return True</span>
 <span class="sd">        &quot;&quot;&quot;</span>
+        <span class="k">if</span> <span class="n">train_iter</span> <span class="o">==</span> <span class="bp">self</span><span class="o">.</span><span class="n">_last_eval_iter</span><span class="p">:</span>
+            <span class="k">return</span> <span class="kc">False</span>
         <span class="k">if</span> <span class="p">(</span><span class="n">train_iter</span> <span class="o">-</span> <span class="bp">self</span><span class="o">.</span><span class="n">_last_eval_iter</span><span class="p">)</span> <span class="o">&lt;</span> <span class="bp">self</span><span class="o">.</span><span class="n">_cfg</span><span class="o">.</span><span class="n">eval_freq</span> <span class="ow">and</span> <span class="n">train_iter</span> <span class="o">!=</span> <span class="mi">0</span><span class="p">:</span>
             <span class="k">return</span> <span class="kc">False</span>
         <span class="bp">self</span><span class="o">.</span><span class="n">_last_eval_iter</span> <span class="o">=</span> <span class="n">train_iter</span>

_sources/feature/policy_overview_en.rst.txt

@@ -58,7 +58,7 @@ Policy Interfaces
 
     * ``_forward_learn`` : Forward method for learn mode.
 
-    * ``_reset_learn`` : Reset learn mode related varaiables if there are any. Do not need to implement this by force.
+    * ``_reset_learn`` : Reset learn mode related variables if there are any. Do not need to implement this by force.
 
     * ``_monitor_vars_learn`` : Variables that are monitored in learner training process. Those variables will be printed to text and tensorboard logger.
 
@@ -70,7 +70,7 @@ Policy Interfaces
 
     * ``_forward_collect`` : Forward method for collect mode.
 
-    * ``_reset_collect`` : Reset collect mode related varaiables if there are any. Do not need to implement this by force.
+    * ``_reset_collect`` : Reset collect mode related variables if there are any. Do not need to implement this by force.
 
     * ``_process_transition`` : Process env timestep and policy output into a transition.
 
@@ -84,7 +84,7 @@ Policy Interfaces
 
     * ``_forward_eval`` : Forward method for eval mode.
 
-    * ``_reset_eval`` : Reset eval mode related varaiables if there are any. Do not need to implement this by force.
+    * ``_reset_eval`` : Reset eval mode related variables if there are any. Do not need to implement this by force.
 
     * ``_state_dict_eval`` : Return model's current state dict.
 

feature/policy_overview_en.html

@@ -244,7 +244,7 @@
 <blockquote>
 <div><ul class="simple">
 <li><p><code class="docutils literal notranslate"><span class="pre">_forward_learn</span></code> : Forward method for learn mode.</p></li>
-<li><p><code class="docutils literal notranslate"><span class="pre">_reset_learn</span></code> : Reset learn mode related varaiables if there are any. Do not need to implement this by force.</p></li>
+<li><p><code class="docutils literal notranslate"><span class="pre">_reset_learn</span></code> : Reset learn mode related variables if there are any. Do not need to implement this by force.</p></li>
 <li><p><code class="docutils literal notranslate"><span class="pre">_monitor_vars_learn</span></code> : Variables that are monitored in learner training process. Those variables will be printed to text and tensorboard logger.</p></li>
 <li><p><code class="docutils literal notranslate"><span class="pre">_state_dict_learn</span></code> : Return model’s current state dict.</p></li>
 <li><p><code class="docutils literal notranslate"><span class="pre">_load_state_dict_learn</span></code> : Load a state dict to model.</p></li>
@@ -255,7 +255,7 @@
 <blockquote>
 <div><ul class="simple">
 <li><p><code class="docutils literal notranslate"><span class="pre">_forward_collect</span></code> : Forward method for collect mode.</p></li>
-<li><p><code class="docutils literal notranslate"><span class="pre">_reset_collect</span></code> : Reset collect mode related varaiables if there are any. Do not need to implement this by force.</p></li>
+<li><p><code class="docutils literal notranslate"><span class="pre">_reset_collect</span></code> : Reset collect mode related variables if there are any. Do not need to implement this by force.</p></li>
 <li><p><code class="docutils literal notranslate"><span class="pre">_process_transition</span></code> : Process env timestep and policy output into a transition.</p></li>
 <li><p><code class="docutils literal notranslate"><span class="pre">_get_train_sample</span></code> : Get samples that could be used for training from a sequence of transitions.</p></li>
 <li><p><code class="docutils literal notranslate"><span class="pre">_state_dict_collect</span></code> : Return model’s current state dict.</p></li>
@@ -267,7 +267,7 @@
 <blockquote>
 <div><ul class="simple">
 <li><p><code class="docutils literal notranslate"><span class="pre">_forward_eval</span></code> : Forward method for eval mode.</p></li>
-<li><p><code class="docutils literal notranslate"><span class="pre">_reset_eval</span></code> : Reset eval mode related varaiables if there are any. Do not need to implement this by force.</p></li>
+<li><p><code class="docutils literal notranslate"><span class="pre">_reset_eval</span></code> : Reset eval mode related variables if there are any. Do not need to implement this by force.</p></li>
 <li><p><code class="docutils literal notranslate"><span class="pre">_state_dict_eval</span></code> : Return model’s current state dict.</p></li>
 <li><p><code class="docutils literal notranslate"><span class="pre">_load_state_dict_eval</span></code> : Load a state dict to model.</p></li>
 </ul>