mirror of
https://github.com/gryf/coach.git
synced 2025-12-17 19:20:19 +01:00
pre-release 0.10.0
This commit is contained in:
Gal Novik
@@ -3,33 +3,29 @@
|
||||
<!--[if gt IE 8]><!--> <html class="no-js" lang="en" > <!--<![endif]-->
|
||||
<head>
|
||||
<meta charset="utf-8">
|
||||
<meta http-equiv="X-UA-Compatible" content="IE=edge">
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0">
|
||||
|
||||
<title>Adding a New Environment - Reinforcement Learning Coach Documentation</title>
|
||||
|
||||
|
||||
<link rel="shortcut icon" href="../../img/favicon.ico">
|
||||
|
||||
|
||||
<title>Adding a New Environment - Reinforcement Learning Coach</title>
|
||||
<link href='https://fonts.googleapis.com/css?family=Lato:400,700|Roboto+Slab:400,700|Inconsolata:400,700' rel='stylesheet' type='text/css'>
|
||||
|
||||
<link rel="stylesheet" href="../../css/theme.css" type="text/css" />
|
||||
<link rel="stylesheet" href="../../css/theme_extra.css" type="text/css" />
|
||||
<link rel="stylesheet" href="../../css/highlight.css">
|
||||
<link href="../../extra.css" rel="stylesheet">
|
||||
|
||||
|
||||
<script>
|
||||
// Current page data
|
||||
var mkdocs_page_name = "Adding a New Environment";
|
||||
var mkdocs_page_input_path = "contributing/add_env.md";
|
||||
var mkdocs_page_url = "/contributing/add_env/";
|
||||
</script>
|
||||
|
||||
<script src="../../js/jquery-2.1.1.min.js"></script>
|
||||
<script src="../../js/modernizr-2.8.3.min.js"></script>
|
||||
<script type="text/javascript" src="../../js/highlight.pack.js"></script>
|
||||
<script src="../../js/theme.js"></script>
|
||||
<script src="https://cdn.mathjax.org/mathjax/latest/MathJax.js?config=TeX-AMS_HTML"></script>
|
||||
|
||||
<script type="text/javascript" src="../../js/highlight.pack.js"></script>
|
||||
|
||||
</head>
|
||||
|
||||
@@ -40,7 +36,7 @@
|
||||
|
||||
<nav data-toggle="wy-nav-shift" class="wy-nav-side stickynav">
|
||||
<div class="wy-side-nav-search">
|
||||
<a href="../.." class="icon icon-home"> Reinforcement Learning Coach Documentation</a>
|
||||
<a href="../.." class="icon icon-home"> Reinforcement Learning Coach</a>
|
||||
<div role="search">
|
||||
<form id ="rtd-search-form" class="wy-form" action="../../search.html" method="get">
|
||||
<input type="text" name="q" placeholder="Search docs" />
|
||||
@@ -49,188 +45,145 @@
|
||||
</div>
|
||||
|
||||
<div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="main navigation">
|
||||
<ul class="current">
|
||||
<ul class="current">
|
||||
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../..">Home</a>
|
||||
|
||||
</li>
|
||||
<li>
|
||||
<li class="toctree-l1">
|
||||
|
||||
<a class="" href="../..">Home</a>
|
||||
</li>
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../design/index.html">Design</a>
|
||||
|
||||
</li>
|
||||
<li>
|
||||
<li class="toctree-l1">
|
||||
|
||||
<a class="" href="../../usage/">Usage</a>
|
||||
</li>
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../usage/index.html">Usage</a>
|
||||
|
||||
</li>
|
||||
<li>
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1">
|
||||
|
||||
<span class="caption-text">Design</span>
|
||||
<ul class="subnav">
|
||||
<li><span>Algorithms</span></li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../algorithms/value_optimization/dqn/index.html">DQN</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../algorithms/value_optimization/double_dqn/index.html">Double DQN</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../algorithms/value_optimization/dueling_dqn/index.html">Dueling DQN</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../algorithms/value_optimization/categorical_dqn/index.html">Categorical DQN</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../algorithms/value_optimization/mmc/index.html">Mixed Monte Carlo</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../algorithms/value_optimization/pal/index.html">Persistent Advantage Learning</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../algorithms/value_optimization/nec/index.html">Neural Episodic Control</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../algorithms/value_optimization/bs_dqn/index.html">Bootstrapped DQN</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../algorithms/value_optimization/n_step/index.html">N-Step Q Learning</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../algorithms/value_optimization/naf/index.html">Normalized Advantage Functions</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../algorithms/policy_optimization/pg/index.html">Policy Gradient</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../algorithms/policy_optimization/ac/index.html">Actor-Critic</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../algorithms/policy_optimization/ddpg/index.html">Deep Determinstic Policy Gradients</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../algorithms/policy_optimization/ppo/index.html">Proximal Policy Optimization</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../algorithms/policy_optimization/cppo/index.html">Clipped Proximal Policy Optimization</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../algorithms/other/dfp/index.html">Direct Future Prediction</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../algorithms/imitation/bc/index.html">Behavioral Cloning</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../design/features/">Features</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../design/control_flow/">Control Flow</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../design/network/">Network</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../design/filters/">Filters</a>
|
||||
</li>
|
||||
</ul>
|
||||
<li>
|
||||
</li>
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../dashboard/index.html">Coach Dashboard</a>
|
||||
|
||||
</li>
|
||||
<li>
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1">
|
||||
|
||||
<span class="caption-text">Algorithms</span>
|
||||
<ul class="subnav">
|
||||
<li><span>Contributing</span></li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../add_agent/index.html">Adding a New Agent</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 current">
|
||||
<a class="current" href="./index.html">Adding a New Environment</a>
|
||||
|
||||
<ul>
|
||||
|
||||
</ul>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../algorithms/value_optimization/dqn/">DQN</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../algorithms/value_optimization/double_dqn/">Double DQN</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../algorithms/value_optimization/dueling_dqn/">Dueling DQN</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../algorithms/value_optimization/categorical_dqn/">Categorical DQN</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../algorithms/value_optimization/mmc/">Mixed Monte Carlo</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../algorithms/value_optimization/pal/">Persistent Advantage Learning</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../algorithms/value_optimization/nec/">Neural Episodic Control</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../algorithms/value_optimization/bs_dqn/">Bootstrapped DQN</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../algorithms/value_optimization/n_step/">N-Step Q Learning</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../algorithms/value_optimization/naf/">Normalized Advantage Functions</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../algorithms/policy_optimization/pg/">Policy Gradient</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../algorithms/policy_optimization/ac/">Actor-Critic</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../algorithms/policy_optimization/ddpg/">Deep Determinstic Policy Gradients</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../algorithms/policy_optimization/ppo/">Proximal Policy Optimization</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../algorithms/policy_optimization/cppo/">Clipped Proximal Policy Optimization</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../algorithms/other/dfp/">Direct Future Prediction</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../algorithms/imitation/bc/">Behavioral Cloning</a>
|
||||
</li>
|
||||
</ul>
|
||||
<li>
|
||||
</li>
|
||||
|
||||
<li class="toctree-l1">
|
||||
|
||||
<a class="" href="../../dashboard/">Coach Dashboard</a>
|
||||
</li>
|
||||
|
||||
<li class="toctree-l1">
|
||||
|
||||
<span class="caption-text">Contributing</span>
|
||||
<ul class="subnav">
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../add_agent/">Adding a New Agent</a>
|
||||
</li>
|
||||
<li class=" current">
|
||||
|
||||
<a class="current" href="./">Adding a New Environment</a>
|
||||
<ul class="subnav">
|
||||
|
||||
<li class="toctree-l3"><a href="#using-the-openai-gym-api">Using the OpenAI Gym API</a></li>
|
||||
|
||||
|
||||
<li class="toctree-l3"><a href="#using-the-coach-api">Using the Coach API</a></li>
|
||||
|
||||
|
||||
</ul>
|
||||
</li>
|
||||
</ul>
|
||||
</li>
|
||||
|
||||
</ul>
|
||||
</div>
|
||||
@@ -242,7 +195,7 @@
|
||||
|
||||
<nav class="wy-nav-top" role="navigation" aria-label="top navigation">
|
||||
<i data-toggle="wy-nav-top" class="fa fa-bars"></i>
|
||||
<a href="../..">Reinforcement Learning Coach Documentation</a>
|
||||
<a href="../..">Reinforcement Learning Coach</a>
|
||||
</nav>
|
||||
|
||||
|
||||
@@ -269,74 +222,81 @@
|
||||
<div class="section">
|
||||
|
||||
<p>Adding a new environment to Coach is as easy as solving CartPole. </p>
|
||||
<p>There are essentially two ways to integrate new environments to Coach:</p>
|
||||
<h2 id="using-the-openai-gym-api">Using the OpenAI Gym API</h2>
|
||||
<p>If your environment is already using the OpenAI Gym API, you are already good to go.
|
||||
When selecting the environment parameters in the preset, use GymEnvironmentParameters(),
|
||||
and pass the path to your environment source code using the level parameter.
|
||||
You can specify additional parameters for your environment using the additional_simulator_parameters parameter.
|
||||
Take for example the definition used in the Pendulum_HAC preset:</p>
|
||||
<pre><code> env_params = GymEnvironmentParameters()
|
||||
env_params.level = "rl_coach.environments.mujoco.pendulum_with_goals:PendulumWithGoals"
|
||||
env_params.additional_simulator_parameters = {"time_limit": 1000}
|
||||
</code></pre>
|
||||
<h2 id="using-the-coach-api">Using the Coach API</h2>
|
||||
<p>There are a few simple steps to follow, and we will walk through them one by one.</p>
|
||||
<ol>
|
||||
<li>
|
||||
<p>Coach defines a simple API for implementing a new environment which is defined in environment/environment_wrapper.py.
|
||||
There are several functions to implement, but only some of them are mandatory. </p>
|
||||
<p>Create a new class for your environment, and inherit the Environment class.</p>
|
||||
</li>
|
||||
<li>
|
||||
<p>Coach defines a simple API for implementing a new environment, which are defined in environment/environment.py.
|
||||
There are several functions to implement, but only some of them are mandatory.</p>
|
||||
<p>Here are the important ones:</p>
|
||||
<pre><code> def _take_action(self, action_idx):
|
||||
<pre><code> def _take_action(self, action_idx: ActionType) -> None:
|
||||
"""
|
||||
An environment dependent function that sends an action to the simulator.
|
||||
:param action_idx: the action to perform on the environment.
|
||||
:param action_idx: the action to perform on the environment
|
||||
:return: None
|
||||
"""
|
||||
pass
|
||||
|
||||
def _preprocess_observation(self, observation):
|
||||
"""
|
||||
Do initial observation preprocessing such as cropping, rgb2gray, rescale etc.
|
||||
Implementing this function is optional.
|
||||
:param observation: a raw observation from the environment
|
||||
:return: the preprocessed observation
|
||||
"""
|
||||
return observation
|
||||
|
||||
def _update_state(self):
|
||||
def _update_state(self) -> None:
|
||||
"""
|
||||
Updates the state from the environment.
|
||||
Should update self.observation, self.reward, self.done, self.measurements and self.info
|
||||
:return: None
|
||||
"""
|
||||
pass
|
||||
|
||||
def _restart_environment_episode(self, force_environment_reset=False):
|
||||
def _restart_environment_episode(self, force_environment_reset=False) -> None:
|
||||
"""
|
||||
Restarts the simulator episode
|
||||
:param force_environment_reset: Force the environment to reset even if the episode is not done yet.
|
||||
:return:
|
||||
:return: None
|
||||
"""
|
||||
pass
|
||||
|
||||
def get_rendered_image(self):
|
||||
def _render(self) -> None:
|
||||
"""
|
||||
Renders the environment using the native simulator renderer
|
||||
:return: None
|
||||
"""
|
||||
|
||||
def get_rendered_image(self) -> np.ndarray:
|
||||
"""
|
||||
Return a numpy array containing the image that will be rendered to the screen.
|
||||
This can be different from the observation. For example, mujoco's observation is a measurements vector.
|
||||
:return: numpy array containing the image that will be rendered to the screen
|
||||
"""
|
||||
return self.observation
|
||||
</code></pre>
|
||||
</li>
|
||||
<li>
|
||||
<p>Make sure to import the environment in environments/__init__.py:</p>
|
||||
<pre><code>from doom_environment_wrapper import *
|
||||
</code></pre>
|
||||
<p>Also, a new entry should be added to the EnvTypes enum mapping the environment name to the wrapper's class name:</p>
|
||||
<pre><code>Doom = "DoomEnvironmentWrapper"
|
||||
<p>Create a new parameters class for your environment, which inherits the EnvironmentParameters class.
|
||||
In the <strong>init</strong> of your class, define all the parameters you used in your Environment class.
|
||||
Additionally, fill the path property of the class with the path to your Environment class.
|
||||
For example, take a look at the EnvironmentParameters class used for Doom:</p>
|
||||
<pre><code> class DoomEnvironmentParameters(EnvironmentParameters):
|
||||
def __init__(self):
|
||||
super().__init__()
|
||||
self.default_input_filter = DoomInputFilter
|
||||
self.default_output_filter = DoomOutputFilter
|
||||
self.cameras = [DoomEnvironment.CameraTypes.OBSERVATION]
|
||||
|
||||
@property
|
||||
def path(self):
|
||||
return 'rl_coach.environments.doom_environment:DoomEnvironment'
|
||||
</code></pre>
|
||||
</li>
|
||||
<li>
|
||||
<p>In addition a new configuration class should be implemented for defining the environment's parameters and placed in configurations.py.
|
||||
For instance, the following is used for Doom:</p>
|
||||
<pre><code>class Doom(EnvironmentParameters):
|
||||
type = 'Doom'
|
||||
frame_skip = 4
|
||||
observation_stack_size = 3
|
||||
desired_observation_height = 60
|
||||
desired_observation_width = 76
|
||||
</code></pre>
|
||||
</li>
|
||||
<li>
|
||||
<p>And that's it, you're done. Now just add a new preset with your newly created environment, and start training an agent on top of it. </p>
|
||||
<p>And that's it, you're done. Now just add a new preset with your newly created environment, and start training an agent on top of it.</p>
|
||||
</li>
|
||||
</ol>
|
||||
|
||||
@@ -347,7 +307,7 @@ For instance, the following is used for Doom:</p>
|
||||
<div class="rst-footer-buttons" role="navigation" aria-label="footer navigation">
|
||||
|
||||
|
||||
<a href="../add_agent/index.html" class="btn btn-neutral" title="Adding a New Agent"><span class="icon icon-circle-arrow-left"></span> Previous</a>
|
||||
<a href="../add_agent/" class="btn btn-neutral" title="Adding a New Agent"><span class="icon icon-circle-arrow-left"></span> Previous</a>
|
||||
|
||||
</div>
|
||||
|
||||
@@ -361,7 +321,7 @@ For instance, the following is used for Doom:</p>
|
||||
|
||||
Built with <a href="http://www.mkdocs.org">MkDocs</a> using a <a href="https://github.com/snide/sphinx_rtd_theme">theme</a> provided by <a href="https://readthedocs.org">Read the Docs</a>.
|
||||
</footer>
|
||||
|
||||
|
||||
</div>
|
||||
</div>
|
||||
|
||||
@@ -369,15 +329,20 @@ For instance, the following is used for Doom:</p>
|
||||
|
||||
</div>
|
||||
|
||||
<div class="rst-versions" role="note" style="cursor: pointer">
|
||||
<div class="rst-versions" role="note" style="cursor: pointer">
|
||||
<span class="rst-current-version" data-toggle="rst-current-version">
|
||||
|
||||
|
||||
<span><a href="../add_agent/index.html" style="color: #fcfcfc;">« Previous</a></span>
|
||||
<span><a href="../add_agent/" style="color: #fcfcfc;">« Previous</a></span>
|
||||
|
||||
|
||||
</span>
|
||||
</div>
|
||||
<script>var base_url = '../..';</script>
|
||||
<script src="../../js/theme.js"></script>
|
||||
<script src="https://cdn.mathjax.org/mathjax/latest/MathJax.js?config=TeX-AMS_HTML"></script>
|
||||
<script src="../../search/require.js"></script>
|
||||
<script src="../../search/search.js"></script>
|
||||
|
||||
</body>
|
||||
</html>
|
||||
|
||||
Reference in New Issue
Block a user