gryf/coach
1
0
Fork 0
mirror of https://github.com/gryf/coach.git synced 2025-12-18 03:30:19 +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

91
docs/_modules/rl_coach/environments/gym_environment.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>
@@ -191,6 +196,7 @@
<span class="kn">import</span> <span class="nn">gym</span>
<span class="kn">import</span> <span class="nn">numpy</span> <span class="k">as</span> <span class="nn">np</span>
<span class="kn">from</span> <span class="nn">enum</span> <span class="k">import</span> <span class="n">IntEnum</span>
<span class="kn">import</span> <span class="nn">scipy.ndimage</span>
<span class="kn">from</span> <span class="nn">rl_coach.graph_managers.graph_manager</span> <span class="k">import</span> <span class="n">ScheduleParameters</span>
@@ -219,7 +225,7 @@
<span class="kn">from</span> <span class="nn">rl_coach.core_types</span> <span class="k">import</span> <span class="n">RunPhase</span><span class="p">,</span> <span class="n">EnvironmentSteps</span>
<span class="kn">from</span> <span class="nn">rl_coach.environments.environment</span> <span class="k">import</span> <span class="n">Environment</span><span class="p">,</span> <span class="n">EnvironmentParameters</span><span class="p">,</span> <span class="n">LevelSelection</span>
<span class="kn">from</span> <span class="nn">rl_coach.spaces</span> <span class="k">import</span> <span class="n">DiscreteActionSpace</span><span class="p">,</span> <span class="n">BoxActionSpace</span><span class="p">,</span> <span class="n">ImageObservationSpace</span><span class="p">,</span> <span class="n">VectorObservationSpace</span><span class="p">,</span> \
<span class="n">StateSpace</span><span class="p">,</span> <span class="n">RewardSpace</span>
<span class="n">PlanarMapsObservationSpace</span><span class="p">,</span> <span class="n">TensorObservationSpace</span><span class="p">,</span> <span class="n">StateSpace</span><span class="p">,</span> <span class="n">RewardSpace</span>
<span class="kn">from</span> <span class="nn">rl_coach.filters.filter</span> <span class="k">import</span> <span class="n">NoInputFilter</span><span class="p">,</span> <span class="n">NoOutputFilter</span>
<span class="kn">from</span> <span class="nn">rl_coach.filters.reward.reward_clipping_filter</span> <span class="k">import</span> <span class="n">RewardClippingFilter</span>
<span class="kn">from</span> <span class="nn">rl_coach.filters.observation.observation_rescale_to_size_filter</span> <span class="k">import</span> <span class="n">ObservationRescaleToSizeFilter</span>
@@ -239,6 +245,7 @@
<span class="bp">self</span><span class="o">.</span><span class="n">random_initialization_steps</span> <span class="o">=</span> <span class="mi">0</span>
<span class="bp">self</span><span class="o">.</span><span class="n">max_over_num_frames</span> <span class="o">=</span> <span class="mi">1</span>
<span class="bp">self</span><span class="o">.</span><span class="n">additional_simulator_parameters</span> <span class="o">=</span> <span class="p">{}</span>
<span class="bp">self</span><span class="o">.</span><span class="n">observation_space_type</span> <span class="o">=</span> <span class="kc">None</span>
<span class="nd">@property</span>
<span class="k">def</span> <span class="nf">path</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
@@ -258,7 +265,7 @@
<span class="n">gym_roboschool_envs</span> <span class="o">=</span> <span class="p">[</span><span class="s1">&#39;inverted_pendulum&#39;</span><span class="p">,</span> <span class="s1">&#39;inverted_pendulum_swingup&#39;</span><span class="p">,</span> <span class="s1">&#39;inverted_double_pendulum&#39;</span><span class="p">,</span> <span class="s1">&#39;reacher&#39;</span><span class="p">,</span>
<span class="s1">&#39;hopper&#39;</span><span class="p">,</span> <span class="s1">&#39;walker2d&#39;</span><span class="p">,</span> <span class="s1">&#39;half_cheetah&#39;</span><span class="p">,</span> <span class="s1">&#39;ant&#39;</span><span class="p">,</span> <span class="s1">&#39;humanoid&#39;</span><span class="p">,</span> <span class="s1">&#39;humanoid_flagrun&#39;</span><span class="p">,</span>
<span class="s1">&#39;humanoid_flagrun_harder&#39;</span><span class="p">,</span> <span class="s1">&#39;pong&#39;</span><span class="p">]</span>
<span class="n">roboschool_v0</span> <span class="o">=</span> <span class="p">{</span><span class="n">e</span><span class="p">:</span> <span class="s2">&quot;</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="n">lower_under_to_upper</span><span class="p">(</span><span class="n">e</span><span class="p">)</span> <span class="o">+</span> <span class="s1">&#39;-v0&#39;</span><span class="p">)</span> <span class="k">for</span> <span class="n">e</span> <span class="ow">in</span> <span class="n">gym_roboschool_envs</span><span class="p">}</span>
<span class="n">roboschool_v1</span> <span class="o">=</span> <span class="p">{</span><span class="n">e</span><span class="p">:</span> <span class="s2">&quot;Roboschool</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="n">lower_under_to_upper</span><span class="p">(</span><span class="n">e</span><span class="p">)</span> <span class="o">+</span> <span class="s1">&#39;-v1&#39;</span><span class="p">)</span> <span class="k">for</span> <span class="n">e</span> <span class="ow">in</span> <span class="n">gym_roboschool_envs</span><span class="p">}</span>
<span class="c1"># Mujoco</span>
<span class="n">gym_mujoco_envs</span> <span class="o">=</span> <span class="p">[</span><span class="s1">&#39;inverted_pendulum&#39;</span><span class="p">,</span> <span class="s1">&#39;inverted_double_pendulum&#39;</span><span class="p">,</span> <span class="s1">&#39;reacher&#39;</span><span class="p">,</span> <span class="s1">&#39;hopper&#39;</span><span class="p">,</span> <span class="s1">&#39;walker2d&#39;</span><span class="p">,</span> <span class="s1">&#39;half_cheetah&#39;</span><span class="p">,</span>
@@ -351,11 +358,26 @@
<span class="c1"># Environment</span>
<span class="k">class</span> <span class="nc">ObservationSpaceType</span><span class="p">(</span><span class="n">IntEnum</span><span class="p">):</span>
<span class="n">Tensor</span> <span class="o">=</span> <span class="mi">0</span>
<span class="n">Image</span> <span class="o">=</span> <span class="mi">1</span>
<span class="n">Vector</span> <span class="o">=</span> <span class="mi">2</span>
<div class="viewcode-block" id="GymEnvironment"><a class="viewcode-back" href="../../../components/environments/index.html#rl_coach.environments.gym_environment.GymEnvironment">[docs]</a><span class="k">class</span> <span class="nc">GymEnvironment</span><span class="p">(</span><span class="n">Environment</span><span class="p">):</span>
<span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">level</span><span class="p">:</span> <span class="n">LevelSelection</span><span class="p">,</span> <span class="n">frame_skip</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> <span class="n">visualization_parameters</span><span class="p">:</span> <span class="n">VisualizationParameters</span><span class="p">,</span>
<span class="n">target_success_rate</span><span class="p">:</span> <span class="nb">float</span><span class="o">=</span><span class="mf">1.0</span><span class="p">,</span> <span class="n">additional_simulator_parameters</span><span class="p">:</span> <span class="n">Dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">Any</span><span class="p">]</span> <span class="o">=</span> <span class="p">{},</span> <span class="n">seed</span><span class="p">:</span> <span class="n">Union</span><span class="p">[</span><span class="kc">None</span><span class="p">,</span> <span class="nb">int</span><span class="p">]</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">human_control</span><span class="p">:</span> <span class="nb">bool</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> <span class="n">custom_reward_threshold</span><span class="p">:</span> <span class="n">Union</span><span class="p">[</span><span class="nb">int</span><span class="p">,</span> <span class="nb">float</span><span class="p">]</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">random_initialization_steps</span><span class="p">:</span> <span class="nb">int</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span> <span class="n">max_over_num_frames</span><span class="p">:</span> <span class="nb">int</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span>
<span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span>
<span class="n">level</span><span class="p">:</span> <span class="n">LevelSelection</span><span class="p">,</span>
<span class="n">frame_skip</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span>
<span class="n">visualization_parameters</span><span class="p">:</span> <span class="n">VisualizationParameters</span><span class="p">,</span>
<span class="n">target_success_rate</span><span class="p">:</span> <span class="nb">float</span><span class="o">=</span><span class="mf">1.0</span><span class="p">,</span>
<span class="n">additional_simulator_parameters</span><span class="p">:</span> <span class="n">Dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">Any</span><span class="p">]</span> <span class="o">=</span> <span class="p">{},</span>
<span class="n">seed</span><span class="p">:</span> <span class="n">Union</span><span class="p">[</span><span class="kc">None</span><span class="p">,</span> <span class="nb">int</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span>
<span class="n">human_control</span><span class="p">:</span> <span class="nb">bool</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
<span class="n">custom_reward_threshold</span><span class="p">:</span> <span class="n">Union</span><span class="p">[</span><span class="nb">int</span><span class="p">,</span> <span class="nb">float</span><span class="p">]</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">random_initialization_steps</span><span class="p">:</span> <span class="nb">int</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span>
<span class="n">max_over_num_frames</span><span class="p">:</span> <span class="nb">int</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span>
<span class="n">observation_space_type</span><span class="p">:</span> <span class="n">ObservationSpaceType</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="o">**</span><span class="n">kwargs</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> :param level: (str)</span>
<span class="sd"> A string representing the gym level to run. This can also be a LevelSelection object.</span>
@@ -390,6 +412,11 @@
<span class="sd"> This value will be used for merging multiple frames into a single frame by taking the maximum value for each</span>
<span class="sd"> of the pixels in the frame. This is particularly used in Atari games, where the frames flicker, and objects</span>
<span class="sd"> can be seen in one frame but disappear in the next.</span>
<span class="sd"> :param observation_space_type:</span>
<span class="sd"> This value will be used for generating observation space. Allows a custom space. Should be one of</span>
<span class="sd"> ObservationSpaceType. If not specified, observation space is inferred from the number of dimensions</span>
<span class="sd"> of the observation: 1D: Vector space, 3D: Image space if 1 or 3 channels, PlanarMaps space otherwise.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">level</span><span class="p">,</span> <span class="n">seed</span><span class="p">,</span> <span class="n">frame_skip</span><span class="p">,</span> <span class="n">human_control</span><span class="p">,</span> <span class="n">custom_reward_threshold</span><span class="p">,</span>
<span class="n">visualization_parameters</span><span class="p">,</span> <span class="n">target_success_rate</span><span class="p">)</span>
@@ -455,6 +482,7 @@
<span class="c1"># frame skip and max between consecutive frames</span>
<span class="bp">self</span><span class="o">.</span><span class="n">is_robotics_env</span> <span class="o">=</span> <span class="s1">&#39;robotics&#39;</span> <span class="ow">in</span> <span class="nb">str</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">unwrapped</span><span class="o">.</span><span class="vm">__class__</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">is_mujoco_env</span> <span class="o">=</span> <span class="s1">&#39;mujoco&#39;</span> <span class="ow">in</span> <span class="nb">str</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">unwrapped</span><span class="o">.</span><span class="vm">__class__</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">is_roboschool_env</span> <span class="o">=</span> <span class="s1">&#39;roboschool&#39;</span> <span class="ow">in</span> <span class="nb">str</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">unwrapped</span><span class="o">.</span><span class="vm">__class__</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">is_atari_env</span> <span class="o">=</span> <span class="s1">&#39;Atari&#39;</span> <span class="ow">in</span> <span class="nb">str</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">unwrapped</span><span class="o">.</span><span class="vm">__class__</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">timelimit_env_wrapper</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">env</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">is_atari_env</span><span class="p">:</span>
@@ -479,20 +507,40 @@
<span class="n">state_space</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">observation_space</span><span class="o">.</span><span class="n">spaces</span>
<span class="k">for</span> <span class="n">observation_space_name</span><span class="p">,</span> <span class="n">observation_space</span> <span class="ow">in</span> <span class="n">state_space</span><span class="o">.</span><span class="n">items</span><span class="p">():</span>
<span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">observation_space</span><span class="o">.</span><span class="n">shape</span><span class="p">)</span> <span class="o">==</span> <span class="mi">3</span><span class="p">:</span>
<span class="k">if</span> <span class="n">observation_space_type</span> <span class="o">==</span> <span class="n">ObservationSpaceType</span><span class="o">.</span><span class="n">Tensor</span><span class="p">:</span>
<span class="c1"># we consider arbitrary input tensor which does not necessarily represent images</span>
<span class="bp">self</span><span class="o">.</span><span class="n">state_space</span><span class="p">[</span><span class="n">observation_space_name</span><span class="p">]</span> <span class="o">=</span> <span class="n">TensorObservationSpace</span><span class="p">(</span>
<span class="n">shape</span><span class="o">=</span><span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">(</span><span class="n">observation_space</span><span class="o">.</span><span class="n">shape</span><span class="p">),</span>
<span class="n">low</span><span class="o">=</span><span class="n">observation_space</span><span class="o">.</span><span class="n">low</span><span class="p">,</span>
<span class="n">high</span><span class="o">=</span><span class="n">observation_space</span><span class="o">.</span><span class="n">high</span>
<span class="p">)</span>
<span class="k">elif</span> <span class="n">observation_space_type</span> <span class="o">==</span> <span class="n">ObservationSpaceType</span><span class="o">.</span><span class="n">Image</span> <span class="ow">or</span> <span class="nb">len</span><span class="p">(</span><span class="n">observation_space</span><span class="o">.</span><span class="n">shape</span><span class="p">)</span> <span class="o">==</span> <span class="mi">3</span><span class="p">:</span>
<span class="c1"># we assume gym has image observations (with arbitrary number of channels) where their values are</span>
<span class="c1"># within 0-255, and where the channel dimension is the last dimension</span>
<span class="bp">self</span><span class="o">.</span><span class="n">state_space</span><span class="p">[</span><span class="n">observation_space_name</span><span class="p">]</span> <span class="o">=</span> <span class="n">ImageObservationSpace</span><span class="p">(</span>
<span class="n">shape</span><span class="o">=</span><span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">(</span><span class="n">observation_space</span><span class="o">.</span><span class="n">shape</span><span class="p">),</span>
<span class="n">high</span><span class="o">=</span><span class="mi">255</span><span class="p">,</span>
<span class="n">channels_axis</span><span class="o">=-</span><span class="mi">1</span>
<span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">if</span> <span class="n">observation_space</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="o">-</span><span class="mi">1</span><span class="p">]</span> <span class="ow">in</span> <span class="p">[</span><span class="mi">1</span><span class="p">,</span> <span class="mi">3</span><span class="p">]:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">state_space</span><span class="p">[</span><span class="n">observation_space_name</span><span class="p">]</span> <span class="o">=</span> <span class="n">ImageObservationSpace</span><span class="p">(</span>
<span class="n">shape</span><span class="o">=</span><span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">(</span><span class="n">observation_space</span><span class="o">.</span><span class="n">shape</span><span class="p">),</span>
<span class="n">high</span><span class="o">=</span><span class="mi">255</span><span class="p">,</span>
<span class="n">channels_axis</span><span class="o">=-</span><span class="mi">1</span>
<span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="c1"># For any number of channels other than 1 or 3, use the generic PlanarMaps space</span>
<span class="bp">self</span><span class="o">.</span><span class="n">state_space</span><span class="p">[</span><span class="n">observation_space_name</span><span class="p">]</span> <span class="o">=</span> <span class="n">PlanarMapsObservationSpace</span><span class="p">(</span>
<span class="n">shape</span><span class="o">=</span><span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">(</span><span class="n">observation_space</span><span class="o">.</span><span class="n">shape</span><span class="p">),</span>
<span class="n">low</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span>
<span class="n">high</span><span class="o">=</span><span class="mi">255</span><span class="p">,</span>
<span class="n">channels_axis</span><span class="o">=-</span><span class="mi">1</span>
<span class="p">)</span>
<span class="k">elif</span> <span class="n">observation_space_type</span> <span class="o">==</span> <span class="n">ObservationSpaceType</span><span class="o">.</span><span class="n">Vector</span> <span class="ow">or</span> <span class="nb">len</span><span class="p">(</span><span class="n">observation_space</span><span class="o">.</span><span class="n">shape</span><span class="p">)</span> <span class="o">==</span> <span class="mi">1</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">state_space</span><span class="p">[</span><span class="n">observation_space_name</span><span class="p">]</span> <span class="o">=</span> <span class="n">VectorObservationSpace</span><span class="p">(</span>
<span class="n">shape</span><span class="o">=</span><span class="n">observation_space</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span>
<span class="n">low</span><span class="o">=</span><span class="n">observation_space</span><span class="o">.</span><span class="n">low</span><span class="p">,</span>
<span class="n">high</span><span class="o">=</span><span class="n">observation_space</span><span class="o">.</span><span class="n">high</span>
<span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">raise</span> <span class="n">screen</span><span class="o">.</span><span class="n">error</span><span class="p">(</span><span class="s2">&quot;Failed to instantiate Gym environment class </span><span class="si">%s</span><span class="s2"> with observation space type </span><span class="si">%s</span><span class="s2">&quot;</span> <span class="o">%</span>
<span class="p">(</span><span class="n">env_class</span><span class="p">,</span> <span class="n">observation_space_type</span><span class="p">),</span> <span class="n">crash</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
<span class="k">if</span> <span class="s1">&#39;desired_goal&#39;</span> <span class="ow">in</span> <span class="n">state_space</span><span class="o">.</span><span class="n">keys</span><span class="p">():</span>
<span class="bp">self</span><span class="o">.</span><span class="n">goal_space</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">state_space</span><span class="p">[</span><span class="s1">&#39;desired_goal&#39;</span><span class="p">]</span>
@@ -618,8 +666,7 @@
<span class="sd"> :param camera_idx: The index of the camera to use. Should be defined in the model</span>
<span class="sd"> :return: None</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">unwrapped</span><span class="o">.</span><span class="n">viewer</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> <span class="ow">and</span> <span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">unwrapped</span><span class="o">.</span><span class="n">viewer</span><span class="o">.</span><span class="n">cam</span><span class="o">.</span><span class="n">fixedcamid</span> <span class="o">!=</span> <span class="n">camera_idx</span> <span class="ow">and</span>\
<span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">unwrapped</span><span class="o">.</span><span class="n">viewer</span><span class="o">.</span><span class="n">_ncam</span> <span class="o">&gt;</span> <span class="n">camera_idx</span><span class="p">:</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">unwrapped</span><span class="o">.</span><span class="n">viewer</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> <span class="ow">and</span> <span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">unwrapped</span><span class="o">.</span><span class="n">viewer</span><span class="o">.</span><span class="n">cam</span><span class="o">.</span><span class="n">fixedcamid</span> <span class="o">!=</span> <span class="n">camera_idx</span><span class="p">:</span>
<span class="kn">from</span> <span class="nn">mujoco_py.generated</span> <span class="k">import</span> <span class="n">const</span>
<span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">unwrapped</span><span class="o">.</span><span class="n">viewer</span><span class="o">.</span><span class="n">cam</span><span class="o">.</span><span class="n">type</span> <span class="o">=</span> <span class="n">const</span><span class="o">.</span><span class="n">CAMERA_FIXED</span>
<span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">unwrapped</span><span class="o">.</span><span class="n">viewer</span><span class="o">.</span><span class="n">cam</span><span class="o">.</span><span class="n">fixedcamid</span> <span class="o">=</span> <span class="n">camera_idx</span>
@@ -633,7 +680,7 @@
<span class="k">def</span> <span class="nf">_render</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">render</span><span class="p">(</span><span class="n">mode</span><span class="o">=</span><span class="s1">&#39;human&#39;</span><span class="p">)</span>
<span class="c1"># required for setting up a fixed camera for mujoco</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">is_mujoco_env</span><span class="p">:</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">is_mujoco_env</span> <span class="ow">and</span> <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">is_roboschool_env</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_set_mujoco_camera</span><span class="p">(</span><span class="mi">0</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">get_rendered_image</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
@@ -643,12 +690,20 @@
<span class="k">else</span><span class="p">:</span>
<span class="n">image</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">render</span><span class="p">(</span><span class="n">mode</span><span class="o">=</span><span class="s1">&#39;rgb_array&#39;</span><span class="p">)</span>
<span class="c1"># required for setting up a fixed camera for mujoco</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">is_mujoco_env</span><span class="p">:</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">is_mujoco_env</span> <span class="ow">and</span> <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">is_roboschool_env</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_set_mujoco_camera</span><span class="p">(</span><span class="mi">0</span><span class="p">)</span>
<span class="k">return</span> <span class="n">image</span>
<span class="k">def</span> <span class="nf">get_target_success_rate</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="nb">float</span><span class="p">:</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">target_success_rate</span></div>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">target_success_rate</span>
<span class="k">def</span> <span class="nf">close</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span><span class="p">:</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Clean up to close rendering windows.</span>
<span class="sd"> :return: None</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">close</span><span class="p">()</span></div>
</pre></div>
</div>