gryf/coach
1
0
Fork 0
mirror of https://github.com/gryf/coach.git synced 2025-12-18 19:50:17 +01:00
Code Issues Projects Releases Wiki Activity

Add documentation on distributed Coach. (#158)

Browse Source 
* Added documentation on distributed Coach.
This commit is contained in:
Balaji Subramaniam
2018-11-27 02:26:15 -08:00
committed by Gal Novik
parent e3ecf445e2
commit d06197f663
151 changed files with 5302 additions and 643 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
docs/_modules/rl_coach/agents/ppo_agent.html
View File

@@ -85,6 +85,7 @@
<p class="caption"><span class="caption-text">Intro</span></p>
<ul>
<li class="toctree-l1"><a class="reference internal" href="../../../usage.html">Usage</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../dist_usage.html">Usage - Distributed Coach</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../features/index.html">Features</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../selecting_an_algorithm.html">Selecting an Algorithm</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../dashboard.html">Coach Dashboard</a></li>
@@ -93,6 +94,7 @@
<ul>
<li class="toctree-l1"><a class="reference internal" href="../../../design/control_flow.html">Control Flow</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../design/network.html">Network Design</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../design/horizontal_scaling.html">Distributed Coach - Horizontal Scale-Out</a></li>
</ul>
<p class="caption"><span class="caption-text">Contributing</span></p>
<ul>
@@ -103,10 +105,13 @@
<ul>
<li class="toctree-l1"><a class="reference internal" href="../../../components/agents/index.html">Agents</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../components/architectures/index.html">Architectures</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../components/data_stores/index.html">Data Stores</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../components/environments/index.html">Environments</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../components/exploration_policies/index.html">Exploration Policies</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../components/filters/index.html">Filters</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../components/memories/index.html">Memories</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../components/memory_backends/index.html">Memory Backends</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../components/orchestrators/index.html">Orchestrators</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../components/core_types.html">Core Types</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../components/spaces.html">Spaces</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../components/additional_parameters.html">Additional Parameters</a></li>
@@ -295,7 +300,8 @@
<span class="bp">self</span><span class="o">.</span><span class="n">estimate_state_value_using_gae</span> <span class="o">=</span> <span class="kc">True</span>
<span class="bp">self</span><span class="o">.</span><span class="n">use_kl_regularization</span> <span class="o">=</span> <span class="kc">True</span>
<span class="bp">self</span><span class="o">.</span><span class="n">beta_entropy</span> <span class="o">=</span> <span class="mf">0.01</span>
<span class="bp">self</span><span class="o">.</span><span class="n">num_consecutive_playing_steps</span> <span class="o">=</span> <span class="n">EnvironmentSteps</span><span class="p">(</span><span class="mi">5000</span><span class="p">)</span></div>
<span class="bp">self</span><span class="o">.</span><span class="n">num_consecutive_playing_steps</span> <span class="o">=</span> <span class="n">EnvironmentSteps</span><span class="p">(</span><span class="mi">5000</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">act_for_full_episodes</span> <span class="o">=</span> <span class="kc">True</span></div>
<span class="k">class</span> <span class="nc">PPOAgentParameters</span><span class="p">(</span><span class="n">AgentParameters</span><span class="p">):</span>
@@ -529,12 +535,9 @@
<span class="c1"># clean memory</span>
<span class="bp">self</span><span class="o">.</span><span class="n">call_memory</span><span class="p">(</span><span class="s1">&#39;clean&#39;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">_should_train_helper</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">wait_for_full_episode</span><span class="o">=</span><span class="kc">True</span><span class="p">):</span>
<span class="k">return</span> <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="n">_should_train_helper</span><span class="p">(</span><span class="kc">True</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">train</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="n">loss</span> <span class="o">=</span> <span class="mi">0</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_should_train</span><span class="p">(</span><span class="n">wait_for_full_episode</span><span class="o">=</span><span class="kc">True</span><span class="p">):</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_should_train</span><span class="p">():</span>
<span class="k">for</span> <span class="n">network</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">networks</span><span class="o">.</span><span class="n">values</span><span class="p">():</span>
<span class="n">network</span><span class="o">.</span><span class="n">set_is_training</span><span class="p">(</span><span class="kc">True</span><span class="p">)</span>
@@ -566,6 +569,7 @@
<span class="k">def</span> <span class="nf">get_prediction</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">states</span><span class="p">):</span>
<span class="n">tf_input_state</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">prepare_batch_for_inference</span><span class="p">(</span><span class="n">states</span><span class="p">,</span> <span class="s2">&quot;actor&quot;</span><span class="p">)</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">networks</span><span class="p">[</span><span class="s1">&#39;actor&#39;</span><span class="p">]</span><span class="o">.</span><span class="n">online_network</span><span class="o">.</span><span class="n">predict</span><span class="p">(</span><span class="n">tf_input_state</span><span class="p">)</span>
</pre></div>
</div>