auto-generating sphinx docs

pytorch · Aug 5, 2024 · fb4ceab · fb4ceab
1 parent 06252f8
commit fb4ceab
Show file tree

Hide file tree

Showing 74 changed files with 1,962 additions and 1,958 deletions.
diff --git a/main/_downloads/04340de0748216c2f40fec722b0c537a/coding_ppo.zip b/main/_downloads/04340de0748216c2f40fec722b0c537a/coding_ppo.zip
diff --git a/main/_downloads/081100bf3a52dc1a4dc24370cc84af82/coding_ddpg.zip b/main/_downloads/081100bf3a52dc1a4dc24370cc84af82/coding_ddpg.zip
diff --git a/main/_downloads/124213c5eea0ba072f91efb7f4ed6dd9/rb_tutorial.zip b/main/_downloads/124213c5eea0ba072f91efb7f4ed6dd9/rb_tutorial.zip
diff --git a/main/_downloads/29e38ada65547ef361ed2ee56525e971/coding_dqn.zip b/main/_downloads/29e38ada65547ef361ed2ee56525e971/coding_dqn.zip
diff --git a/main/_downloads/315c4c52fb68082a731b192d944e2ede/tutorials_python.zip b/main/_downloads/315c4c52fb68082a731b192d944e2ede/tutorials_python.zip
diff --git a/main/_downloads/35e7f5fd87ede5f9e265a17f465badd1/pretrained_models.zip b/main/_downloads/35e7f5fd87ede5f9e265a17f465badd1/pretrained_models.zip
diff --git a/main/_downloads/50b0715662e94f3a49e303bdc1969a80/dqn_with_rnn.zip b/main/_downloads/50b0715662e94f3a49e303bdc1969a80/dqn_with_rnn.zip
diff --git a/main/_downloads/5128e829b7152f5a40050c479b691f69/multiagent_competitive_ddpg.zip b/main/_downloads/5128e829b7152f5a40050c479b691f69/multiagent_competitive_ddpg.zip
diff --git a/main/_downloads/53d45db6c317a5dacd743dd31c55d6e3/multi_task.zip b/main/_downloads/53d45db6c317a5dacd743dd31c55d6e3/multi_task.zip
diff --git a/main/_downloads/53e0992e72aa1cea24016933d54c8450/getting-started-2.zip b/main/_downloads/53e0992e72aa1cea24016933d54c8450/getting-started-2.zip
diff --git a/main/_downloads/6788515c42b2ed1b56a3c1a2f0fce644/torchrl_envs.zip b/main/_downloads/6788515c42b2ed1b56a3c1a2f0fce644/torchrl_envs.zip
diff --git a/main/_downloads/6a76fecc1b49e983846e88271a9db64b/getting-started-1.zip b/main/_downloads/6a76fecc1b49e983846e88271a9db64b/getting-started-1.zip
diff --git a/main/_downloads/895258fb3cdda4392121339635f09c16/multiagent_ppo.zip b/main/_downloads/895258fb3cdda4392121339635f09c16/multiagent_ppo.zip
diff --git a/main/_downloads/8f12eae910cb18a3a4c44ea4196bc20d/getting-started-4.zip b/main/_downloads/8f12eae910cb18a3a4c44ea4196bc20d/getting-started-4.zip
diff --git a/main/_downloads/99d42909723ba57785105ef8a42c1535/torchrl_demo.zip b/main/_downloads/99d42909723ba57785105ef8a42c1535/torchrl_demo.zip
diff --git a/main/_downloads/a5659940aa3f8f568547d47752a43172/tutorials_jupyter.zip b/main/_downloads/a5659940aa3f8f568547d47752a43172/tutorials_jupyter.zip
diff --git a/main/_downloads/cf5ed21c138297680764e29dffa8a8af/pendulum.zip b/main/_downloads/cf5ed21c138297680764e29dffa8a8af/pendulum.zip
diff --git a/main/_downloads/dad3f0a1f7722e8534bfbd892b0c68bd/getting-started-0.zip b/main/_downloads/dad3f0a1f7722e8534bfbd892b0c68bd/getting-started-0.zip
diff --git a/main/_downloads/eca47ab9308c1987e81fb27ca2532496/getting-started-5.zip b/main/_downloads/eca47ab9308c1987e81fb27ca2532496/getting-started-5.zip
diff --git a/main/_downloads/fbaa3b91355e869868174ff484447abe/getting-started-3.zip b/main/_downloads/fbaa3b91355e869868174ff484447abe/getting-started-3.zip
diff --git a/main/_images/sphx_glr_coding_ddpg_001.png b/main/_images/sphx_glr_coding_ddpg_001.png
diff --git a/main/_images/sphx_glr_coding_ddpg_thumb.png b/main/_images/sphx_glr_coding_ddpg_thumb.png
diff --git a/main/_images/sphx_glr_coding_ppo_001.png b/main/_images/sphx_glr_coding_ppo_001.png
diff --git a/main/_images/sphx_glr_coding_ppo_thumb.png b/main/_images/sphx_glr_coding_ppo_thumb.png
diff --git a/main/_images/sphx_glr_dqn_with_rnn_001.png b/main/_images/sphx_glr_dqn_with_rnn_001.png
diff --git a/main/_images/sphx_glr_dqn_with_rnn_thumb.png b/main/_images/sphx_glr_dqn_with_rnn_thumb.png
diff --git a/main/_images/sphx_glr_rb_tutorial_001.png b/main/_images/sphx_glr_rb_tutorial_001.png
diff --git a/main/_images/sphx_glr_rb_tutorial_002.png b/main/_images/sphx_glr_rb_tutorial_002.png
diff --git a/main/_images/sphx_glr_rb_tutorial_thumb.png b/main/_images/sphx_glr_rb_tutorial_thumb.png
diff --git a/main/_images/sphx_glr_torchrl_envs_001.png b/main/_images/sphx_glr_torchrl_envs_001.png
diff --git a/main/_modules/torchrl/data/tensor_specs.html b/main/_modules/torchrl/data/tensor_specs.html
@@ -4523,7 +4523,7 @@ <h1>Source code for torchrl.data.tensor_specs</h1><div class="highlight"><pre>
         <span class="k">for</span> <span class="n">key</span><span class="p">,</span> <span class="n">item</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_specs</span><span class="o">.</span><span class="n">items</span><span class="p">():</span>
             <span class="k">if</span> <span class="n">item</span> <span class="ow">is</span> <span class="kc">None</span> <span class="ow">or</span> <span class="p">(</span><span class="nb">isinstance</span><span class="p">(</span><span class="n">item</span><span class="p">,</span> <span class="n">CompositeSpec</span><span class="p">)</span> <span class="ow">and</span> <span class="n">item</span><span class="o">.</span><span class="n">is_empty</span><span class="p">()):</span>
                 <span class="k">continue</span>
-            <span class="n">val_item</span> <span class="o">=</span> <span class="n">val</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">key</span><span class="p">)</span>
+            <span class="n">val_item</span> <span class="o">=</span> <span class="n">val</span><span class="p">[</span><span class="n">key</span><span class="p">]</span>
             <span class="k">if</span> <span class="ow">not</span> <span class="n">item</span><span class="o">.</span><span class="n">is_in</span><span class="p">(</span><span class="n">val_item</span><span class="p">):</span>
                 <span class="k">return</span> <span class="kc">False</span>
         <span class="k">return</span> <span class="kc">True</span></div>

diff --git a/main/_modules/torchrl/envs/transforms/transforms.html b/main/_modules/torchrl/envs/transforms/transforms.html
@@ -6003,7 +6003,7 @@ <h1>Source code for torchrl.envs.transforms.transforms</h1><div class="highlight
             <span class="p">)</span>
         <span class="n">time_dim</span> <span class="o">=</span> <span class="n">time_dim</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="o">-</span> <span class="mi">1</span>
         <span class="k">for</span> <span class="n">in_key</span><span class="p">,</span> <span class="n">out_key</span> <span class="ow">in</span> <span class="nb">zip</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">in_keys</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">out_keys</span><span class="p">):</span>
-            <span class="n">reward</span> <span class="o">=</span> <span class="n">tensordict</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">in_key</span><span class="p">)</span>
+            <span class="n">reward</span> <span class="o">=</span> <span class="n">tensordict</span><span class="p">[</span><span class="n">in_key</span><span class="p">]</span>
             <span class="n">cumsum</span> <span class="o">=</span> <span class="n">reward</span><span class="o">.</span><span class="n">cumsum</span><span class="p">(</span><span class="n">time_dim</span><span class="p">)</span>
             <span class="n">tensordict</span><span class="o">.</span><span class="n">set</span><span class="p">(</span><span class="n">out_key</span><span class="p">,</span> <span class="n">cumsum</span><span class="p">)</span>
         <span class="k">return</span> <span class="n">tensordict</span></div></div>

diff --git a/main/_modules/torchrl/modules/tensordict_module/rnn.html b/main/_modules/torchrl/modules/tensordict_module/rnn.html
@@ -1067,7 +1067,7 @@ <h1>Source code for torchrl.modules.tensordict_module.rnn</h1><div class="highli
         <span class="k">else</span><span class="p">:</span>
             <span class="n">tensordict_shaped</span> <span class="o">=</span> <span class="n">tensordict</span><span class="o">.</span><span class="n">reshape</span><span class="p">(</span><span class="o">-</span><span class="mi">1</span><span class="p">)</span><span class="o">.</span><span class="n">unsqueeze</span><span class="p">(</span><span class="o">-</span><span class="mi">1</span><span class="p">)</span>
 
-        <span class="n">is_init</span> <span class="o">=</span> <span class="n">tensordict_shaped</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s2">&quot;is_init&quot;</span><span class="p">)</span><span class="o">.</span><span class="n">squeeze</span><span class="p">(</span><span class="o">-</span><span class="mi">1</span><span class="p">)</span>
+        <span class="n">is_init</span> <span class="o">=</span> <span class="n">tensordict_shaped</span><span class="p">[</span><span class="s2">&quot;is_init&quot;</span><span class="p">]</span><span class="o">.</span><span class="n">squeeze</span><span class="p">(</span><span class="o">-</span><span class="mi">1</span><span class="p">)</span>
         <span class="n">splits</span> <span class="o">=</span> <span class="kc">None</span>
         <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">recurrent_mode</span> <span class="ow">and</span> <span class="n">is_init</span><span class="p">[</span><span class="o">...</span><span class="p">,</span> <span class="mi">1</span><span class="p">:]</span><span class="o">.</span><span class="n">any</span><span class="p">():</span>
             <span class="c1"># if we have consecutive trajectories, things get a little more complicated</span>
@@ -1081,7 +1081,7 @@ <h1>Source code for torchrl.modules.tensordict_module.rnn</h1><div class="highli
             <span class="n">tensordict_shaped</span> <span class="o">=</span> <span class="n">_split_and_pad_sequence</span><span class="p">(</span>
                 <span class="n">tensordict_shaped</span><span class="o">.</span><span class="n">select</span><span class="p">(</span><span class="o">*</span><span class="bp">self</span><span class="o">.</span><span class="n">in_keys</span><span class="p">,</span> <span class="n">strict</span><span class="o">=</span><span class="kc">False</span><span class="p">),</span> <span class="n">splits</span>
             <span class="p">)</span>
-            <span class="n">is_init</span> <span class="o">=</span> <span class="n">tensordict_shaped</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s2">&quot;is_init&quot;</span><span class="p">)</span><span class="o">.</span><span class="n">squeeze</span><span class="p">(</span><span class="o">-</span><span class="mi">1</span><span class="p">)</span>
+            <span class="n">is_init</span> <span class="o">=</span> <span class="n">tensordict_shaped</span><span class="p">[</span><span class="s2">&quot;is_init&quot;</span><span class="p">]</span><span class="o">.</span><span class="n">squeeze</span><span class="p">(</span><span class="o">-</span><span class="mi">1</span><span class="p">)</span>
 
         <span class="n">value</span><span class="p">,</span> <span class="n">hidden0</span><span class="p">,</span> <span class="n">hidden1</span> <span class="o">=</span> <span class="p">(</span>
             <span class="n">tensordict_shaped</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">key</span><span class="p">,</span> <span class="n">default</span><span class="p">)</span>
@@ -1812,7 +1812,7 @@ <h1>Source code for torchrl.modules.tensordict_module.rnn</h1><div class="highli
         <span class="k">else</span><span class="p">:</span>
             <span class="n">tensordict_shaped</span> <span class="o">=</span> <span class="n">tensordict</span><span class="o">.</span><span class="n">reshape</span><span class="p">(</span><span class="o">-</span><span class="mi">1</span><span class="p">)</span><span class="o">.</span><span class="n">unsqueeze</span><span class="p">(</span><span class="o">-</span><span class="mi">1</span><span class="p">)</span>
 
-        <span class="n">is_init</span> <span class="o">=</span> <span class="n">tensordict_shaped</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s2">&quot;is_init&quot;</span><span class="p">)</span><span class="o">.</span><span class="n">squeeze</span><span class="p">(</span><span class="o">-</span><span class="mi">1</span><span class="p">)</span>
+        <span class="n">is_init</span> <span class="o">=</span> <span class="n">tensordict_shaped</span><span class="p">[</span><span class="s2">&quot;is_init&quot;</span><span class="p">]</span><span class="o">.</span><span class="n">squeeze</span><span class="p">(</span><span class="o">-</span><span class="mi">1</span><span class="p">)</span>
         <span class="n">splits</span> <span class="o">=</span> <span class="kc">None</span>
         <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">recurrent_mode</span> <span class="ow">and</span> <span class="n">is_init</span><span class="p">[</span><span class="o">...</span><span class="p">,</span> <span class="mi">1</span><span class="p">:]</span><span class="o">.</span><span class="n">any</span><span class="p">():</span>
             <span class="c1"># if we have consecutive trajectories, things get a little more complicated</span>
@@ -1826,7 +1826,7 @@ <h1>Source code for torchrl.modules.tensordict_module.rnn</h1><div class="highli
             <span class="n">tensordict_shaped</span> <span class="o">=</span> <span class="n">_split_and_pad_sequence</span><span class="p">(</span>
                 <span class="n">tensordict_shaped</span><span class="o">.</span><span class="n">select</span><span class="p">(</span><span class="o">*</span><span class="bp">self</span><span class="o">.</span><span class="n">in_keys</span><span class="p">,</span> <span class="n">strict</span><span class="o">=</span><span class="kc">False</span><span class="p">),</span> <span class="n">splits</span>
             <span class="p">)</span>
-            <span class="n">is_init</span> <span class="o">=</span> <span class="n">tensordict_shaped</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s2">&quot;is_init&quot;</span><span class="p">)</span><span class="o">.</span><span class="n">squeeze</span><span class="p">(</span><span class="o">-</span><span class="mi">1</span><span class="p">)</span>
+            <span class="n">is_init</span> <span class="o">=</span> <span class="n">tensordict_shaped</span><span class="p">[</span><span class="s2">&quot;is_init&quot;</span><span class="p">]</span><span class="o">.</span><span class="n">squeeze</span><span class="p">(</span><span class="o">-</span><span class="mi">1</span><span class="p">)</span>
 
         <span class="n">value</span><span class="p">,</span> <span class="n">hidden</span> <span class="o">=</span> <span class="p">(</span>
             <span class="n">tensordict_shaped</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">key</span><span class="p">,</span> <span class="n">default</span><span class="p">)</span>

diff --git a/main/_sources/sg_execution_times.rst.txt b/main/_sources/sg_execution_times.rst.txt
@@ -6,7 +6,7 @@
 
 Computation times
 =================
-**27:02.293** total execution time for 18 files **from all galleries**:
+**26:15.979** total execution time for 18 files **from all galleries**:
 
 .. container::
 
@@ -33,56 +33,56 @@ Computation times
      - Time
      - Mem (MB)
    * - :ref:`sphx_glr_tutorials_torchrl_demo.py` (``reference/generated/tutorials/torchrl_demo.py``)
-     - 03:48.674
-     - 324.8
+     - 03:40.603
+     - 324.4
    * - :ref:`sphx_glr_tutorials_rb_tutorial.py` (``reference/generated/tutorials/rb_tutorial.py``)
-     - 02:57.116
-     - 478.9
+     - 02:50.733
+     - 504.2
    * - :ref:`sphx_glr_tutorials_pendulum.py` (``reference/generated/tutorials/pendulum.py``)
-     - 02:41.646
+     - 02:35.663
      - 316.9
    * - :ref:`sphx_glr_tutorials_coding_dqn.py` (``reference/generated/tutorials/coding_dqn.py``)
-     - 02:38.824
-     - 1226.0
+     - 02:34.786
+     - 954.9
    * - :ref:`sphx_glr_tutorials_dqn_with_rnn.py` (``reference/generated/tutorials/dqn_with_rnn.py``)
-     - 02:19.232
-     - 2171.1
+     - 02:16.723
+     - 2178.8
    * - :ref:`sphx_glr_tutorials_multiagent_ppo.py` (``reference/generated/tutorials/multiagent_ppo.py``)
-     - 02:06.247
-     - 339.4
+     - 02:03.021
+     - 319.3
    * - :ref:`sphx_glr_tutorials_coding_ddpg.py` (``reference/generated/tutorials/coding_ddpg.py``)
-     - 01:53.092
-     - 326.4
+     - 01:49.126
+     - 326.3
    * - :ref:`sphx_glr_tutorials_torchrl_envs.py` (``reference/generated/tutorials/torchrl_envs.py``)
-     - 01:36.773
-     - 4103.0
+     - 01:33.266
+     - 2965.1
    * - :ref:`sphx_glr_tutorials_coding_ppo.py` (``reference/generated/tutorials/coding_ppo.py``)
-     - 01:26.423
-     - 318.9
+     - 01:23.619
+     - 318.3
    * - :ref:`sphx_glr_tutorials_multiagent_competitive_ddpg.py` (``reference/generated/tutorials/multiagent_competitive_ddpg.py``)
-     - 00:59.711
-     - 4284.0
+     - 00:57.606
+     - 3125.0
    * - :ref:`sphx_glr_tutorials_pretrained_models.py` (``reference/generated/tutorials/pretrained_models.py``)
-     - 00:53.502
-     - 3646.2
+     - 00:53.203
+     - 2486.5
    * - :ref:`sphx_glr_tutorials_multi_task.py` (``reference/generated/tutorials/multi_task.py``)
-     - 00:50.955
-     - 318.1
+     - 00:49.199
+     - 318.0
    * - :ref:`sphx_glr_tutorials_getting-started-1.py` (``reference/generated/tutorials/getting-started-1.py``)
-     - 00:46.393
-     - 316.8
+     - 00:44.687
+     - 316.5
    * - :ref:`sphx_glr_tutorials_getting-started-0.py` (``reference/generated/tutorials/getting-started-0.py``)
-     - 00:43.178
+     - 00:43.490
      - 317.7
    * - :ref:`sphx_glr_tutorials_getting-started-2.py` (``reference/generated/tutorials/getting-started-2.py``)
-     - 00:25.051
-     - 321.1
-   * - :ref:`sphx_glr_tutorials_getting-started-5.py` (``reference/generated/tutorials/getting-started-5.py``)
-     - 00:21.162
-     - 354.3
+     - 00:25.262
+     - 320.5
    * - :ref:`sphx_glr_tutorials_getting-started-3.py` (``reference/generated/tutorials/getting-started-3.py``)
-     - 00:20.639
+     - 00:20.764
      - 318.5
+   * - :ref:`sphx_glr_tutorials_getting-started-5.py` (``reference/generated/tutorials/getting-started-5.py``)
+     - 00:20.447
+     - 321.2
    * - :ref:`sphx_glr_tutorials_getting-started-4.py` (``reference/generated/tutorials/getting-started-4.py``)
-     - 00:13.675
-     - 347.6
+     - 00:13.780
+     - 348.6