Deploying to gh-pages from @ 1ed8afc 🚀

05_api_doc/data/buffer/middleware/clone_object.html

@@ -310,16 +310,6 @@ <h1>data.buffer.middleware.clone_object<a class="headerlink" href="#data-buffer-
 <h2>clone_object<a class="headerlink" href="#clone-object" title="Permalink to this headline">¶</a></h2>
 <section id="id1">
 <h3>clone_object<a class="headerlink" href="#id1" title="Permalink to this headline">¶</a></h3>
-<dl class="py function">
-<dt class="sig sig-object py" id="ding.data.buffer.middleware.clone_object.clone_object">
-<span class="sig-prename descclassname"><span class="pre">ding.data.buffer.middleware.clone_object.</span></span><span class="sig-name descname"><span class="pre">clone_object</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference internal" href="../../../../_modules/ding/data/buffer/middleware/clone_object.html#clone_object"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#ding.data.buffer.middleware.clone_object.clone_object" title="Permalink to this definition">¶</a></dt>
-<dd><dl class="simple">
-<dt>Overview:</dt><dd><p>This middleware freezes the objects saved in memory buffer and return copies during sampling,
-try this middleware when you need to keep the object unchanged in buffer, and modify        the object after sampling it (usually in multiple threads)</p>
-</dd>
-</dl>
-</dd></dl>
-
 </section>
 </section>
 </section>

05_api_doc/data/buffer/middleware/group_sample.html

@@ -310,21 +310,6 @@ <h1>data.buffer.middleware.group_sample<a class="headerlink" href="#data-buffer-
 <h2>group_sample<a class="headerlink" href="#group-sample" title="Permalink to this headline">¶</a></h2>
 <section id="id1">
 <h3>group_sample<a class="headerlink" href="#id1" title="Permalink to this headline">¶</a></h3>
-<dl class="py function">
-<dt class="sig sig-object py" id="ding.data.buffer.middleware.group_sample.group_sample">
-<span class="sig-prename descclassname"><span class="pre">ding.data.buffer.middleware.group_sample.</span></span><span class="sig-name descname"><span class="pre">group_sample</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">size_in_group</span></span><span class="p"><span class="pre">:</span></span> <span class="n"><span class="pre">int</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ordered_in_group</span></span><span class="p"><span class="pre">:</span></span> <span class="n"><span class="pre">bool</span></span> <span class="o"><span class="pre">=</span></span> <span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_use_in_group</span></span><span class="p"><span class="pre">:</span></span> <span class="n"><span class="pre">bool</span></span> <span class="o"><span class="pre">=</span></span> <span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><span class="pre">Callable</span></span></span><a class="reference internal" href="../../../../_modules/ding/data/buffer/middleware/group_sample.html#group_sample"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#ding.data.buffer.middleware.group_sample.group_sample" title="Permalink to this definition">¶</a></dt>
-<dd><dl class="simple">
-<dt>Overview:</dt><dd><p>The middleware is designed to process the data in each group after sampling from the buffer.</p>
-</dd>
-<dt>Arguments:</dt><dd><ul class="simple">
-<li><p>size_in_group (<code class="xref py py-obj docutils literal notranslate"><span class="pre">int</span></code>): Sample size in each group.</p></li>
-<li><p>ordered_in_group (<code class="xref py py-obj docutils literal notranslate"><span class="pre">bool</span></code>): Whether to keep the original order of records, default is true.</p></li>
-<li><p>max_use_in_group (<code class="xref py py-obj docutils literal notranslate"><span class="pre">bool</span></code>): Whether to use as much data in each group as possible, default is true.</p></li>
-</ul>
-</dd>
-</dl>
-</dd></dl>
-
 </section>
 </section>
 </section>

05_api_doc/data/buffer/middleware/padding.html

@@ -310,21 +310,6 @@ <h1>data.buffer.middleware.padding<a class="headerlink" href="#data-buffer-middl
 <h2>padding<a class="headerlink" href="#padding" title="Permalink to this headline">¶</a></h2>
 <section id="id1">
 <h3>padding<a class="headerlink" href="#id1" title="Permalink to this headline">¶</a></h3>
-<dl class="py function">
-<dt class="sig sig-object py" id="ding.data.buffer.middleware.padding.padding">
-<span class="sig-prename descclassname"><span class="pre">ding.data.buffer.middleware.padding.</span></span><span class="sig-name descname"><span class="pre">padding</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">policy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'random'</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="../../../../_modules/ding/data/buffer/middleware/padding.html#padding"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#ding.data.buffer.middleware.padding.padding" title="Permalink to this definition">¶</a></dt>
-<dd><dl class="simple">
-<dt>Overview:</dt><dd><p>Fill the nested buffer list to the same size as the largest list.
-The default policy <cite>random</cite> will randomly select data from each group
-and fill it into the current group list.</p>
-</dd>
-<dt>Arguments:</dt><dd><ul class="simple">
-<li><p>policy (<code class="xref py py-obj docutils literal notranslate"><span class="pre">str</span></code>): Padding policy, supports <cite>random</cite>, <cite>none</cite>.</p></li>
-</ul>
-</dd>
-</dl>
-</dd></dl>
-
 </section>
 </section>
 </section>

05_api_doc/data/buffer/middleware/priority.html

@@ -310,30 +310,6 @@ <h1>data.buffer.middleware.priority<a class="headerlink" href="#data-buffer-midd
 <h2>priority<a class="headerlink" href="#priority" title="Permalink to this headline">¶</a></h2>
 <section id="priorityexperiencereplay">
 <h3>PriorityExperienceReplay<a class="headerlink" href="#priorityexperiencereplay" title="Permalink to this headline">¶</a></h3>
-<dl class="py class">
-<dt class="sig sig-object py" id="ding.data.buffer.middleware.priority.PriorityExperienceReplay">
-<em class="property"><span class="pre">class</span> </em><span class="sig-prename descclassname"><span class="pre">ding.data.buffer.middleware.priority.</span></span><span class="sig-name descname"><span class="pre">PriorityExperienceReplay</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">buffer</span></span><span class="p"><span class="pre">:</span></span> <span class="n"><span class="pre">Buffer</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">IS_weight</span></span><span class="p"><span class="pre">:</span></span> <span class="n"><span class="pre">bool</span></span> <span class="o"><span class="pre">=</span></span> <span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">priority_power_factor</span></span><span class="p"><span class="pre">:</span></span> <span class="n"><span class="pre">float</span></span> <span class="o"><span class="pre">=</span></span> <span class="default_value"><span class="pre">0.6</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">IS_weight_power_factor</span></span><span class="p"><span class="pre">:</span></span> <span class="n"><span class="pre">float</span></span> <span class="o"><span class="pre">=</span></span> <span class="default_value"><span class="pre">0.4</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">IS_weight_anneal_train_iter</span></span><span class="p"><span class="pre">:</span></span> <span class="n"><span class="pre">int</span></span> <span class="o"><span class="pre">=</span></span> <span class="default_value"><span class="pre">100000</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="../../../../_modules/ding/data/buffer/middleware/priority.html#PriorityExperienceReplay"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#ding.data.buffer.middleware.priority.PriorityExperienceReplay" title="Permalink to this definition">¶</a></dt>
-<dd><dl class="simple">
-<dt>Overview:</dt><dd><p>The middleware that implements priority experience replay (PER).</p>
-</dd>
-</dl>
-<dl class="py method">
-<dt class="sig sig-object py" id="ding.data.buffer.middleware.priority.PriorityExperienceReplay.__init__">
-<span class="sig-name descname"><span class="pre">__init__</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">buffer</span></span><span class="p"><span class="pre">:</span></span> <span class="n"><span class="pre">Buffer</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">IS_weight</span></span><span class="p"><span class="pre">:</span></span> <span class="n"><span class="pre">bool</span></span> <span class="o"><span class="pre">=</span></span> <span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">priority_power_factor</span></span><span class="p"><span class="pre">:</span></span> <span class="n"><span class="pre">float</span></span> <span class="o"><span class="pre">=</span></span> <span class="default_value"><span class="pre">0.6</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">IS_weight_power_factor</span></span><span class="p"><span class="pre">:</span></span> <span class="n"><span class="pre">float</span></span> <span class="o"><span class="pre">=</span></span> <span class="default_value"><span class="pre">0.4</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">IS_weight_anneal_train_iter</span></span><span class="p"><span class="pre">:</span></span> <span class="n"><span class="pre">int</span></span> <span class="o"><span class="pre">=</span></span> <span class="default_value"><span class="pre">100000</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><span class="pre">None</span></span></span><a class="reference internal" href="../../../../_modules/ding/data/buffer/middleware/priority.html#PriorityExperienceReplay.__init__"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#ding.data.buffer.middleware.priority.PriorityExperienceReplay.__init__" title="Permalink to this definition">¶</a></dt>
-<dd><dl class="simple">
-<dt>Arguments:</dt><dd><ul class="simple">
-<li><p>buffer (<code class="xref py py-obj docutils literal notranslate"><span class="pre">Buffer</span></code>): The buffer to use PER.</p></li>
-<li><p>IS_weight (<code class="xref py py-obj docutils literal notranslate"><span class="pre">bool</span></code>): Whether use importance sampling or not.</p></li>
-<li><p>priority_power_factor (<code class="xref py py-obj docutils literal notranslate"><span class="pre">float</span></code>): The factor that adjust the sensitivity between                the sampling probability and the priority level.</p></li>
-<li><p>IS_weight_power_factor (<code class="xref py py-obj docutils literal notranslate"><span class="pre">float</span></code>): The factor that adjust the sensitivity between                the sample rarity and sampling probability in importance sampling.</p></li>
-<li><p>IS_weight_anneal_train_iter (<code class="xref py py-obj docutils literal notranslate"><span class="pre">float</span></code>): The factor that controls the increasing of                <code class="docutils literal notranslate"><span class="pre">IS_weight_power_factor</span></code> during training.</p></li>
-</ul>
-</dd>
-</dl>
-</dd></dl>
-
-</dd></dl>
-
 </section>
 </section>
 </section>

05_api_doc/data/buffer/middleware/sample_range_view.html

@@ -310,20 +310,6 @@ <h1>data.buffer.middleware.sample_range_view<a class="headerlink" href="#data-bu
 <h2>sample_range_view<a class="headerlink" href="#sample-range-view" title="Permalink to this headline">¶</a></h2>
 <section id="id1">
 <h3>sample_range_view<a class="headerlink" href="#id1" title="Permalink to this headline">¶</a></h3>
-<dl class="py function">
-<dt class="sig sig-object py" id="ding.data.buffer.middleware.sample_range_view.sample_range_view">
-<span class="sig-prename descclassname"><span class="pre">ding.data.buffer.middleware.sample_range_view.</span></span><span class="sig-name descname"><span class="pre">sample_range_view</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">buffer_</span></span><span class="p"><span class="pre">:</span></span> <span class="n"><span class="pre">Buffer</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">start</span></span><span class="p"><span class="pre">:</span></span> <span class="n"><span class="pre">Optional</span><span class="p"><span class="pre">[</span></span><span class="pre">int</span><span class="p"><span class="pre">]</span></span></span> <span class="o"><span class="pre">=</span></span> <span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">end</span></span><span class="p"><span class="pre">:</span></span> <span class="n"><span class="pre">Optional</span><span class="p"><span class="pre">[</span></span><span class="pre">int</span><span class="p"><span class="pre">]</span></span></span> <span class="o"><span class="pre">=</span></span> <span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><span class="pre">Callable</span></span></span><a class="reference internal" href="../../../../_modules/ding/data/buffer/middleware/sample_range_view.html#sample_range_view"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#ding.data.buffer.middleware.sample_range_view.sample_range_view" title="Permalink to this definition">¶</a></dt>
-<dd><dl class="simple">
-<dt>Overview:</dt><dd><p>The middleware that places restrictions on the range of indices during sampling.</p>
-</dd>
-<dt>Arguments:</dt><dd><ul class="simple">
-<li><p>start (<code class="xref py py-obj docutils literal notranslate"><span class="pre">int</span></code>): The starting index.</p></li>
-<li><p>end (<code class="xref py py-obj docutils literal notranslate"><span class="pre">int</span></code>): One above the ending index.</p></li>
-</ul>
-</dd>
-</dl>
-</dd></dl>
-
 </section>
 </section>
 </section>

05_api_doc/data/buffer/middleware/staleness_check.html

@@ -310,21 +310,6 @@ <h1>data.buffer.middleware.staleness_check<a class="headerlink" href="#data-buff
 <h2>staleness_check<a class="headerlink" href="#staleness-check" title="Permalink to this headline">¶</a></h2>
 <section id="id1">
 <h3>staleness_check<a class="headerlink" href="#id1" title="Permalink to this headline">¶</a></h3>
-<dl class="py function">
-<dt class="sig sig-object py" id="ding.data.buffer.middleware.staleness_check.staleness_check">
-<span class="sig-prename descclassname"><span class="pre">ding.data.buffer.middleware.staleness_check.</span></span><span class="sig-name descname"><span class="pre">staleness_check</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">buffer_</span></span><span class="p"><span class="pre">:</span></span> <span class="n"><span class="pre">Buffer</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_staleness</span></span><span class="p"><span class="pre">:</span></span> <span class="n"><span class="pre">int</span></span> <span class="o"><span class="pre">=</span></span> <span class="default_value"><span class="pre">inf</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><span class="pre">Callable</span></span></span><a class="reference internal" href="../../../../_modules/ding/data/buffer/middleware/staleness_check.html#staleness_check"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#ding.data.buffer.middleware.staleness_check.staleness_check" title="Permalink to this definition">¶</a></dt>
-<dd><dl class="simple">
-<dt>Overview:</dt><dd><p>This middleware aims to check staleness before each sample operation,
-staleness = train_iter_sample_data - train_iter_data_collected, means how old/off-policy the data is,
-If data’s staleness is greater(&gt;) than max_staleness, this data will be removed from buffer as soon as possible.</p>
-</dd>
-<dt>Arguments:</dt><dd><ul class="simple">
-<li><p>max_staleness (<code class="xref py py-obj docutils literal notranslate"><span class="pre">int</span></code>): The maximum legal span between the time of collecting and time of sampling.</p></li>
-</ul>
-</dd>
-</dl>
-</dd></dl>
-
 </section>
 </section>
 </section>

05_api_doc/data/buffer/middleware/use_time_check.html

@@ -310,20 +310,6 @@ <h1>data.buffer.middleware.use_time_check<a class="headerlink" href="#data-buffe
 <h2>use_time_check<a class="headerlink" href="#use-time-check" title="Permalink to this headline">¶</a></h2>
 <section id="id1">
 <h3>use_time_check<a class="headerlink" href="#id1" title="Permalink to this headline">¶</a></h3>
-<dl class="py function">
-<dt class="sig sig-object py" id="ding.data.buffer.middleware.use_time_check.use_time_check">
-<span class="sig-prename descclassname"><span class="pre">ding.data.buffer.middleware.use_time_check.</span></span><span class="sig-name descname"><span class="pre">use_time_check</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">buffer_</span></span><span class="p"><span class="pre">:</span></span> <span class="n"><span class="pre">Buffer</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_use</span></span><span class="p"><span class="pre">:</span></span> <span class="n"><span class="pre">int</span></span> <span class="o"><span class="pre">=</span></span> <span class="default_value"><span class="pre">inf</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><span class="pre">Callable</span></span></span><a class="reference internal" href="../../../../_modules/ding/data/buffer/middleware/use_time_check.html#use_time_check"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#ding.data.buffer.middleware.use_time_check.use_time_check" title="Permalink to this definition">¶</a></dt>
-<dd><dl class="simple">
-<dt>Overview:</dt><dd><p>This middleware aims to check the usage times of data in buffer. If the usage times of a data is
-greater than or equal to max_use, this data will be removed from buffer as soon as possible.</p>
-</dd>
-<dt>Arguments:</dt><dd><ul class="simple">
-<li><p>max_use (<code class="xref py py-obj docutils literal notranslate"><span class="pre">int</span></code>): The max reused (resampled) count for any individual object.</p></li>
-</ul>
-</dd>
-</dl>
-</dd></dl>
-
 </section>
 </section>
 </section>