mirror of
https://github.com/Farama-Foundation/Gymnasium.git
synced 2025-08-19 13:32:03 +00:00
796 lines
57 KiB
HTML
796 lines
57 KiB
HTML
<!doctype html>
|
||
<html class="no-js" lang="en">
|
||
<head><meta charset="utf-8"/>
|
||
<meta name="viewport" content="width=device-width,initial-scale=1"/>
|
||
<meta name="color-scheme" content="light dark">
|
||
<meta name="description" content="A standard API for reinforcement learning and a diverse set of reference environments (formerly Gym)">
|
||
<meta property="og:title" content="Gymnasium Documentation" />
|
||
<meta property="og:type" content="website" />
|
||
<meta property="og:description" content="A standard API for reinforcement learning and a diverse set of reference environments (formerly Gym)" />
|
||
<meta property="og:url" content="https://gymnasium.farama.org/content/basic_usage.html" /><meta property="og:image" content="https://gymnasium.farama.org/_static/img/gymnasium-github.png" /><meta name="twitter:card" content="summary_large_image"><meta name="generator" content="Docutils 0.19: https://docutils.sourceforge.io/" />
|
||
<link rel="index" title="Index" href="../../genindex/" /><link rel="search" title="Search" href="../../search/" /><link rel="next" title="Compatibility with Gym" href="../gym_compatibility/" /><link rel="prev" title="Gymnasium is a standard API for reinforcement learning, and a diverse collection of reference environments" href="../../" />
|
||
<link rel="canonical" href="https://gymnasium.farama.org/content/basic_usage.html" />
|
||
|
||
<link rel="shortcut icon" href="../../_static/favicon.png"/><meta name="generator" content="sphinx-5.3.0, furo 2022.09.15.dev1"/>
|
||
<title>Basic Usage - Gymnasium Documentation</title>
|
||
<link rel="stylesheet" type="text/css" href="../../_static/pygments.css" />
|
||
<link rel="stylesheet" type="text/css" href="../../_static/styles/furo.css?digest=9ec31e2665bf879c1d47d93a8ec4893870ee1e45" />
|
||
<link rel="stylesheet" type="text/css" href="../../_static/styles/furo-extensions.css?digest=a614025deca43086db03c234d5a3a2047a0241ae" />
|
||
|
||
|
||
|
||
|
||
<style>
|
||
body {
|
||
--color-code-background: #f8f8f8;
|
||
--color-code-foreground: black;
|
||
|
||
}
|
||
@media not print {
|
||
body[data-theme="dark"] {
|
||
--color-code-background: #202020;
|
||
--color-code-foreground: #d0d0d0;
|
||
|
||
}
|
||
@media (prefers-color-scheme: dark) {
|
||
body:not([data-theme="light"]) {
|
||
--color-code-background: #202020;
|
||
--color-code-foreground: #d0d0d0;
|
||
|
||
}
|
||
}
|
||
}
|
||
</style></head>
|
||
<body>
|
||
<header class="farama-header">
|
||
<div class="farama-header__container">
|
||
<div class="farama-header__left">
|
||
<a href="../../">
|
||
<img class="farama-header__logo only-light" src="../../_static/img/gymnasium_black.svg" alt="Light Logo"/>
|
||
<img class="farama-header__logo only-dark" src="../../_static/img/gymnasium_white.svg" alt="Dark Logo"/>
|
||
<h1 class="farama-header__title">Gymnasium Documentation</h1>
|
||
</a>
|
||
</div>
|
||
<div class="farama-header__right">
|
||
<div class="farama-header-menu">
|
||
<div class="farama-header-menu__btn">
|
||
<span class="farama-header-menu__btn-name">
|
||
Farama Foundation
|
||
</span>
|
||
<svg viewBox="0 0 32 32" xmlns="http://www.w3.org/2000/svg" xmlns:bx="https://boxy-svg.com">
|
||
<defs></defs>
|
||
<path d="M 3 4.677 C 3 3.751 3.659 3 4.474 3 L 27.526 3 C 28.341 3 29 3.751 29 4.677 C 29 5.603 28.341 6.354 27.526 6.354 L 4.474 6.354 C 3.659 6.354 3 5.603 3 4.677 Z" bx:origin="0.622825 3.875593"></path>
|
||
<path d="M 3 16 C 3 15.074 3.659 14.323 4.474 14.323 L 27.526 14.323 C 28.341 14.323 29 15.074 29 16 C 29 16.926 28.341 17.677 27.526 17.677 L 4.474 17.677 C 3.659 17.677 3 16.926 3 16 Z" bx:origin="0.622825 0.5"></path>
|
||
<path d="M 3 27.323 C 3 26.397 3.659 25.646 4.474 25.646 L 27.526 25.646 C 28.341 25.646 29 26.397 29 27.323 C 29 28.249 28.341 29 27.526 29 L 4.474 29 C 3.659 29 3 28.249 3 27.323 Z" bx:origin="0.622825 -2.875591"></path>
|
||
</svg>
|
||
</div>
|
||
<div class="farama-header-menu-container">
|
||
<div class="farama-header-menu__header">
|
||
<a href="https://farama.org">
|
||
<img class="farama-header-menu__logo" src="../../_static/img/farama_solid_white.svg" alt="Farama Foundation">
|
||
<span>Farama Foundation</span>
|
||
</a>
|
||
<button id="farama-close-menu">
|
||
<svg viewBox="0 0 24 24" xmlns="http://www.w3.org/2000/svg" fill="none" stroke="currentColor"
|
||
stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="icon-close">
|
||
<line x1="3" y1="21" x2="21" y2="3"></line>
|
||
<line x1="3" y1="3" x2="21" y2="21"></line>
|
||
</svg>
|
||
</button>
|
||
</div>
|
||
<div class="farama-header-menu__body">
|
||
<div class="farama-header-menu__section" style="padding-left: 24px;" >
|
||
<span class="farama-header-menu__section-title">Documentation</span>
|
||
<ul class="farama-header-menu-list">
|
||
<li>
|
||
<a href="https://gymnasium.farama.org">
|
||
|
||
<img src="../../_static/img/gymnasium-white.svg">
|
||
|
||
Gymnasium
|
||
</a>
|
||
</li>
|
||
<li>
|
||
<a href="https://pettingzoo.farama.org">
|
||
|
||
<img src="../../_static/img/pettingzoo-white.svg">
|
||
|
||
PettingZoo
|
||
</a>
|
||
</li>
|
||
<li>
|
||
<a href="https://minigrid.farama.org">
|
||
|
||
<img src="../../_static/img/minigrid-white.svg">
|
||
|
||
MiniGrid
|
||
</a>
|
||
</li>
|
||
<li>
|
||
<a href="https://robotics.farama.org">
|
||
|
||
<img src="../../_static/img/gymrobotics-white.svg">
|
||
|
||
Gymnasium-Robotics
|
||
</a>
|
||
</li>
|
||
|
||
</ul>
|
||
</div>
|
||
<div class="farama-header-menu__section" style="padding-left: 24px;" >
|
||
<span class="farama-header-menu__section-title">Mature Projects</span>
|
||
<ul class="farama-header-menu-list">
|
||
<li>
|
||
<a href="https://github.com/Farama-Foundation/SuperSuit">
|
||
|
||
<img src="../../_static/img/supersuit-white.svg">
|
||
|
||
SuperSuit
|
||
</a>
|
||
</li>
|
||
<li>
|
||
<a href="https://github.com/Farama-Foundation/tinyscaler">
|
||
|
||
<img src="../../_static/img/tinyscaler-white.svg">
|
||
|
||
Tinyscaler
|
||
</a>
|
||
</li>
|
||
<li>
|
||
<a href="https://github.com/Farama-Foundation/AutoROM">
|
||
|
||
<img src="../../_static/img/autorom-white.svg">
|
||
|
||
AutoROM
|
||
</a>
|
||
</li>
|
||
<li>
|
||
<a href="https://github.com/Farama-Foundation/Jumpy">
|
||
|
||
<img src="../../_static/img/jumpy-white.svg">
|
||
|
||
JumPy
|
||
</a>
|
||
</li>
|
||
|
||
</ul>
|
||
</div>
|
||
<div class="farama-header-menu__section" style="padding-left: 24px;" >
|
||
<span class="farama-header-menu__section-title">Incubating Projects</span>
|
||
<ul class="farama-header-menu-list">
|
||
<li>
|
||
<a href="https://github.com/Farama-Foundation/MAgent2">
|
||
|
||
<img src="../../_static/img/MAgent2-white.svg">
|
||
|
||
MAgent2
|
||
</a>
|
||
</li>
|
||
<li>
|
||
<a href="https://github.com/Farama-Foundation/procgen2">
|
||
|
||
<img src="../../_static/img/procgen2-white.svg">
|
||
|
||
Procgen2
|
||
</a>
|
||
</li>
|
||
<li>
|
||
<a href="https://github.com/Farama-Foundation/MiniWorld">
|
||
|
||
<img src="../../_static/img/miniworld-white.svg">
|
||
|
||
Miniworld
|
||
</a>
|
||
</li>
|
||
<li>
|
||
<a href="https://github.com/Farama-Foundation/D4RL">
|
||
|
||
<img src="../../_static/img/d4rl-white.svg">
|
||
|
||
D4RL
|
||
</a>
|
||
</li>
|
||
<li>
|
||
<a href="https://github.com/Farama-Foundation/Kabuki">
|
||
|
||
<img src="../../_static/img/kabuki-white.svg">
|
||
|
||
Kabuki
|
||
</a>
|
||
</li>
|
||
|
||
</ul>
|
||
</div>
|
||
<div class="farama-header-menu__section" style="padding-left: 24px;" >
|
||
<span class="farama-header-menu__section-title">Foundation</span>
|
||
<ul class="farama-header-menu-list">
|
||
<li>
|
||
<a href="https://farama.org/about">
|
||
|
||
About
|
||
</a>
|
||
</li>
|
||
<li>
|
||
<a href="https://farama.org/project_standards">
|
||
|
||
Standards
|
||
</a>
|
||
</li>
|
||
<li>
|
||
<a href="https://farama.org/donations">
|
||
|
||
Donate
|
||
</a>
|
||
</li>
|
||
|
||
</ul>
|
||
</div>
|
||
|
||
|
||
</div>
|
||
</div>
|
||
</div>
|
||
</div>
|
||
</div>
|
||
</header>
|
||
|
||
<div class="farama-header-menu__overlay"></div>
|
||
|
||
|
||
<script>
|
||
document.body.dataset.theme = localStorage.getItem("theme") || "auto";
|
||
</script>
|
||
|
||
|
||
<svg xmlns="http://www.w3.org/2000/svg" style="display: none;">
|
||
<symbol id="svg-toc" viewBox="0 0 24 24">
|
||
<title>Contents</title>
|
||
<svg stroke="currentColor" fill="currentColor" stroke-width="0" viewBox="0 0 1024 1024">
|
||
<path d="M408 442h480c4.4 0 8-3.6 8-8v-56c0-4.4-3.6-8-8-8H408c-4.4 0-8 3.6-8 8v56c0 4.4 3.6 8 8 8zm-8 204c0 4.4 3.6 8 8 8h480c4.4 0 8-3.6 8-8v-56c0-4.4-3.6-8-8-8H408c-4.4 0-8 3.6-8 8v56zm504-486H120c-4.4 0-8 3.6-8 8v56c0 4.4 3.6 8 8 8h784c4.4 0 8-3.6 8-8v-56c0-4.4-3.6-8-8-8zm0 632H120c-4.4 0-8 3.6-8 8v56c0 4.4 3.6 8 8 8h784c4.4 0 8-3.6 8-8v-56c0-4.4-3.6-8-8-8zM115.4 518.9L271.7 642c5.8 4.6 14.4.5 14.4-6.9V388.9c0-7.4-8.5-11.5-14.4-6.9L115.4 505.1a8.74 8.74 0 0 0 0 13.8z"/>
|
||
</svg>
|
||
</symbol>
|
||
<symbol id="svg-menu" viewBox="0 0 24 24">
|
||
<title>Menu</title>
|
||
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24" fill="none" stroke="currentColor"
|
||
stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="feather-menu">
|
||
<line x1="3" y1="12" x2="21" y2="12"></line>
|
||
<line x1="3" y1="6" x2="21" y2="6"></line>
|
||
<line x1="3" y1="18" x2="21" y2="18"></line>
|
||
</svg>
|
||
</symbol>
|
||
<symbol id="svg-arrow-right" viewBox="0 0 24 24">
|
||
<title>Expand</title>
|
||
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24" fill="none" stroke="currentColor"
|
||
stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="feather-chevron-right">
|
||
<polyline points="9 18 15 12 9 6"></polyline>
|
||
</svg>
|
||
</symbol>
|
||
<symbol id="svg-sun" viewBox="0 0 24 24">
|
||
<title>Light mode</title>
|
||
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24" fill="none" stroke="currentColor"
|
||
stroke-width="1.5" stroke-linecap="round" stroke-linejoin="round" class="feather-sun">
|
||
<circle cx="12" cy="12" r="5"></circle>
|
||
<line x1="12" y1="1" x2="12" y2="3"></line>
|
||
<line x1="12" y1="21" x2="12" y2="23"></line>
|
||
<line x1="4.22" y1="4.22" x2="5.64" y2="5.64"></line>
|
||
<line x1="18.36" y1="18.36" x2="19.78" y2="19.78"></line>
|
||
<line x1="1" y1="12" x2="3" y2="12"></line>
|
||
<line x1="21" y1="12" x2="23" y2="12"></line>
|
||
<line x1="4.22" y1="19.78" x2="5.64" y2="18.36"></line>
|
||
<line x1="18.36" y1="5.64" x2="19.78" y2="4.22"></line>
|
||
</svg>
|
||
</symbol>
|
||
<symbol id="svg-moon" viewBox="0 0 24 24">
|
||
<title>Dark mode</title>
|
||
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24" fill="none" stroke="currentColor"
|
||
stroke-width="1.5" stroke-linecap="round" stroke-linejoin="round" class="icon-tabler-moon">
|
||
<path stroke="none" d="M0 0h24v24H0z" fill="none" />
|
||
<path d="M12 3c.132 0 .263 0 .393 0a7.5 7.5 0 0 0 7.92 12.446a9 9 0 1 1 -8.313 -12.454z" />
|
||
</svg>
|
||
</symbol>
|
||
<symbol id="svg-sun-half" viewBox="0 0 24 24">
|
||
<title>Auto light/dark mode</title>
|
||
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24" fill="none" stroke="currentColor"
|
||
stroke-width="1.5" stroke-linecap="round" stroke-linejoin="round" class="icon-tabler-shadow">
|
||
<path stroke="none" d="M0 0h24v24H0z" fill="none"/>
|
||
<circle cx="12" cy="12" r="9" />
|
||
<path d="M13 12h5" />
|
||
<path d="M13 15h4" />
|
||
<path d="M13 18h1" />
|
||
<path d="M13 9h4" />
|
||
<path d="M13 6h1" />
|
||
</svg>
|
||
</symbol>
|
||
</svg>
|
||
|
||
<input type="checkbox" class="sidebar-toggle" name="__navigation" id="__navigation">
|
||
<input type="checkbox" class="sidebar-toggle" name="__toc" id="__toc">
|
||
<label class="overlay sidebar-overlay" for="__navigation">
|
||
<div class="visually-hidden">Hide navigation sidebar</div>
|
||
</label>
|
||
<label class="overlay toc-overlay" for="__toc">
|
||
<div class="visually-hidden">Hide table of contents sidebar</div>
|
||
</label>
|
||
|
||
|
||
|
||
<div class="page">
|
||
<header class="mobile-header">
|
||
<div class="header-left">
|
||
<label class="nav-overlay-icon" for="__navigation">
|
||
<div class="visually-hidden">Toggle site navigation sidebar</div>
|
||
<i class="icon"><svg><use href="#svg-menu"></use></svg></i>
|
||
</label>
|
||
</div>
|
||
<div class="header-center">
|
||
<a href="../../"><div class="brand">Gymnasium Documentation</div></a>
|
||
</div>
|
||
<div class="header-right">
|
||
<div class="theme-toggle-container theme-toggle-header">
|
||
<button class="theme-toggle">
|
||
<div class="visually-hidden">Toggle Light / Dark / Auto color theme</div>
|
||
<svg class="theme-icon-when-auto"><use href="#svg-sun-half"></use></svg>
|
||
<svg class="theme-icon-when-dark"><use href="#svg-moon"></use></svg>
|
||
<svg class="theme-icon-when-light"><use href="#svg-sun"></use></svg>
|
||
</button>
|
||
</div>
|
||
<label class="toc-overlay-icon toc-header-icon" for="__toc">
|
||
<div class="visually-hidden">Toggle table of contents sidebar</div>
|
||
<i class="icon"><svg><use href="#svg-toc"></use></svg></i>
|
||
</label>
|
||
</div>
|
||
</header>
|
||
<aside class="sidebar-drawer">
|
||
<div class="sidebar-container">
|
||
|
||
<div class="sidebar-sticky"><form class="sidebar-search-container" method="get" action="../../search/" role="search">
|
||
<input class="sidebar-search" placeholder=Search name="q" aria-label="Search">
|
||
<input type="hidden" name="check_keywords" value="yes">
|
||
<input type="hidden" name="area" value="default">
|
||
</form>
|
||
<div id="searchbox"></div><div class="sidebar-scroll"><div class="sidebar-tree">
|
||
<p class="caption" role="heading"><span class="caption-text">Introduction</span></p>
|
||
<ul class="current">
|
||
<li class="toctree-l1 current current-page"><a class="current reference internal" href="#">Basic Usage</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../gym_compatibility/">Compatibility with Gym</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../migration-guide/">v21 to v26 Migration Guide</a></li>
|
||
</ul>
|
||
<p class="caption" role="heading"><span class="caption-text">API</span></p>
|
||
<ul>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../api/env/">Env</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../api/registry/">Registry</a></li>
|
||
<li class="toctree-l1 has-children"><a class="reference internal" href="../../api/spaces/">Spaces</a><input class="toctree-checkbox" id="toctree-checkbox-1" name="toctree-checkbox-1" role="switch" type="checkbox"/><label for="toctree-checkbox-1"><div class="visually-hidden">Toggle child pages in navigation</div><i class="icon"><svg><use href="#svg-arrow-right"></use></svg></i></label><ul>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../api/spaces/fundamental/">Fundamental Spaces</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../api/spaces/composite/">Composite Spaces</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../api/spaces/utils/">Spaces Utils</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../api/spaces/vector_utils/">Spaces Vector Utils</a></li>
|
||
</ul>
|
||
</li>
|
||
<li class="toctree-l1 has-children"><a class="reference internal" href="../../api/wrappers/">Wrappers</a><input class="toctree-checkbox" id="toctree-checkbox-2" name="toctree-checkbox-2" role="switch" type="checkbox"/><label for="toctree-checkbox-2"><div class="visually-hidden">Toggle child pages in navigation</div><i class="icon"><svg><use href="#svg-arrow-right"></use></svg></i></label><ul>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../api/wrappers/misc_wrappers/">Misc Wrappers</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../api/wrappers/action_wrappers/">Action Wrappers</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../api/wrappers/observation_wrappers/">Observation Wrappers</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../api/wrappers/reward_wrappers/">Reward Wrappers</a></li>
|
||
</ul>
|
||
</li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../api/vector/">Vector</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../api/utils/">Utils</a></li>
|
||
</ul>
|
||
<p class="caption" role="heading"><span class="caption-text">Environments</span></p>
|
||
<ul>
|
||
<li class="toctree-l1 has-children"><a class="reference internal" href="../../environments/classic_control/">Classic Control</a><input class="toctree-checkbox" id="toctree-checkbox-3" name="toctree-checkbox-3" role="switch" type="checkbox"/><label for="toctree-checkbox-3"><div class="visually-hidden">Toggle child pages in navigation</div><i class="icon"><svg><use href="#svg-arrow-right"></use></svg></i></label><ul>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../environments/classic_control/acrobot/">Acrobot</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../environments/classic_control/cart_pole/">Cart Pole</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../environments/classic_control/mountain_car_continuous/">Mountain Car Continuous</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../environments/classic_control/mountain_car/">Mountain Car</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../environments/classic_control/pendulum/">Pendulum</a></li>
|
||
</ul>
|
||
</li>
|
||
<li class="toctree-l1 has-children"><a class="reference internal" href="../../environments/box2d/">Box2D</a><input class="toctree-checkbox" id="toctree-checkbox-4" name="toctree-checkbox-4" role="switch" type="checkbox"/><label for="toctree-checkbox-4"><div class="visually-hidden">Toggle child pages in navigation</div><i class="icon"><svg><use href="#svg-arrow-right"></use></svg></i></label><ul>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../environments/box2d/bipedal_walker/">Bipedal Walker</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../environments/box2d/car_racing/">Car Racing</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../environments/box2d/lunar_lander/">Lunar Lander</a></li>
|
||
</ul>
|
||
</li>
|
||
<li class="toctree-l1 has-children"><a class="reference internal" href="../../environments/toy_text/">Toy Text</a><input class="toctree-checkbox" id="toctree-checkbox-5" name="toctree-checkbox-5" role="switch" type="checkbox"/><label for="toctree-checkbox-5"><div class="visually-hidden">Toggle child pages in navigation</div><i class="icon"><svg><use href="#svg-arrow-right"></use></svg></i></label><ul>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../environments/toy_text/blackjack/">Blackjack</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../environments/toy_text/taxi/">Taxi</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../environments/toy_text/cliff_walking/">Cliff Walking</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../environments/toy_text/frozen_lake/">Frozen Lake</a></li>
|
||
</ul>
|
||
</li>
|
||
<li class="toctree-l1 has-children"><a class="reference internal" href="../../environments/mujoco/">MuJoCo</a><input class="toctree-checkbox" id="toctree-checkbox-6" name="toctree-checkbox-6" role="switch" type="checkbox"/><label for="toctree-checkbox-6"><div class="visually-hidden">Toggle child pages in navigation</div><i class="icon"><svg><use href="#svg-arrow-right"></use></svg></i></label><ul>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../environments/mujoco/ant/">Ant</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../environments/mujoco/half_cheetah/">Half Cheetah</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../environments/mujoco/hopper/">Hopper</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../environments/mujoco/humanoid_standup/">Humanoid Standup</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../environments/mujoco/humanoid/">Humanoid</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../environments/mujoco/inverted_double_pendulum/">Inverted Double Pendulum</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../environments/mujoco/inverted_pendulum/">Inverted Pendulum</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../environments/mujoco/reacher/">Reacher</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../environments/mujoco/swimmer/">Swimmer</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../environments/mujoco/pusher/">Pusher</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../environments/mujoco/walker2d/">Walker2D</a></li>
|
||
</ul>
|
||
</li>
|
||
<li class="toctree-l1 has-children"><a class="reference internal" href="../../environments/atari/">Atari</a><input class="toctree-checkbox" id="toctree-checkbox-7" name="toctree-checkbox-7" role="switch" type="checkbox"/><label for="toctree-checkbox-7"><div class="visually-hidden">Toggle child pages in navigation</div><i class="icon"><svg><use href="#svg-arrow-right"></use></svg></i></label><ul>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../environments/atari/adventure/">Adventure</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../environments/atari/air_raid/">Air Raid</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../environments/atari/alien/">Alien</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../environments/atari/amidar/">Amidar</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../environments/atari/assault/">Assault</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../environments/atari/asterix/">Asterix</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../environments/atari/asteroids/">Asteroids</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../environments/atari/atlantis/">Atlantis</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../environments/atari/bank_heist/">Bank Heist</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../environments/atari/battle_zone/">Battle Zone</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../environments/atari/beam_rider/">Beam Rider</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../environments/atari/berzerk/">Berzerk</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../environments/atari/bowling/">Bowling</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../environments/atari/boxing/">Boxing</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../environments/atari/breakout/">Breakout</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../environments/atari/carnival/">Carnival</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../environments/atari/centipede/">Centipede</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../environments/atari/chopper_command/">Chopper Command</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../environments/atari/crazy_climber/">Crazy Climber</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../environments/atari/defender/">Defender</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../environments/atari/demon_attack/">Demon Attack</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../environments/atari/double_dunk/">Double Dunk</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../environments/atari/elevator_action/">Elevator Action</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../environments/atari/enduro/">Enduro</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../environments/atari/fishing_derby/">FishingDerby</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../environments/atari/freeway/">Freeway</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../environments/atari/frostbite/">Frostbite</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../environments/atari/gopher/">Gopher</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../environments/atari/gravitar/">Gravitar</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../environments/atari/hero/">Hero</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../environments/atari/ice_hockey/">IceHockey</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../environments/atari/jamesbond/">Jamesbond</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../environments/atari/journey_escape/">JourneyEscape</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../environments/atari/kangaroo/">Kangaroo</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../environments/atari/krull/">Krull</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../environments/atari/kung_fu_master/">Kung Fu Master</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../environments/atari/montezuma_revenge/">Montezuma Revenge</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../environments/atari/ms_pacman/">Ms Pacman</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../environments/atari/name_this_game/">Name This Game</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../environments/atari/phoenix/">Phoenix</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../environments/atari/pitfall/">Pitfall</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../environments/atari/pong/">Pong</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../environments/atari/pooyan/">Pooyan</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../environments/atari/private_eye/">PrivateEye</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../environments/atari/qbert/">Qbert</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../environments/atari/riverraid/">Riverraid</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../environments/atari/road_runner/">Road Runner</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../environments/atari/robotank/">Robot Tank</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../environments/atari/seaquest/">Seaquest</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../environments/atari/skiing/">Skiings</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../environments/atari/solaris/">Solaris</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../environments/atari/space_invaders/">SpaceInvaders</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../environments/atari/star_gunner/">StarGunner</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../environments/atari/tennis/">Tennis</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../environments/atari/time_pilot/">TimePilot</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../environments/atari/tutankham/">Tutankham</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../environments/atari/up_n_down/">Up n’ Down</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../environments/atari/venture/">Venture</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../environments/atari/video_pinball/">Video Pinball</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../environments/atari/wizard_of_wor/">Wizard of Wor</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../environments/atari/zaxxon/">Zaxxon</a></li>
|
||
</ul>
|
||
</li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../environments/third_party_environments/">Third-Party Environments</a></li>
|
||
</ul>
|
||
<p class="caption" role="heading"><span class="caption-text">Tutorials</span></p>
|
||
<ul>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../tutorials/blackjack_tutorial/">Solving Blackjack with Q-Learning</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../tutorials/environment_creation/">Make your own custom environment</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../tutorials/handling_time_limits/">Handling Time Limits</a></li>
|
||
</ul>
|
||
<p class="caption" role="heading"><span class="caption-text">Development</span></p>
|
||
<ul>
|
||
<li class="toctree-l1"><a class="reference external" href="https://github.com/Farama-Foundation/Gymnasium">Github</a></li>
|
||
<li class="toctree-l1"><a class="reference external" href="https://github.com/Farama-Foundation/Gymnasium/blob/main/docs/README.md">Contribute to the Docs</a></li>
|
||
</ul>
|
||
|
||
</div>
|
||
</div>
|
||
|
||
</div>
|
||
|
||
</div>
|
||
</aside>
|
||
<div class="main">
|
||
<div class="content">
|
||
<div class="article-container">
|
||
<a href="#" class="back-to-top muted-link">
|
||
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24">
|
||
<path d="M13 20h-2V8l-5.5 5.5-1.42-1.42L12 4.16l7.92 7.92-1.42 1.42L13 8v12z"></path>
|
||
</svg>
|
||
<span>Back to top</span>
|
||
</a>
|
||
<div class="content-icon-container">
|
||
|
||
|
||
<div class="edit-this-page">
|
||
<a class="muted-link" href="https://github.com/Farama-Foundation/Gymnasium/edit/main/docs/content/basic_usage.md" title="Edit this page">
|
||
<svg aria-hidden="true" viewBox="0 0 24 24" stroke-width="1.5" stroke="currentColor" fill="none" stroke-linecap="round" stroke-linejoin="round">
|
||
<path stroke="none" d="M0 0h24v24H0z" fill="none"/>
|
||
<path d="M4 20h4l10.5 -10.5a1.5 1.5 0 0 0 -4 -4l-10.5 10.5v4" />
|
||
<line x1="13.5" y1="6.5" x2="17.5" y2="10.5" />
|
||
</svg>
|
||
<span class="visually-hidden">Edit this page</span>
|
||
</a>
|
||
</div><div class="theme-toggle-container theme-toggle-content">
|
||
<button class="theme-toggle">
|
||
<div class="visually-hidden">Toggle Light / Dark / Auto color theme</div>
|
||
<svg class="theme-icon-when-auto"><use href="#svg-sun-half"></use></svg>
|
||
<svg class="theme-icon-when-dark"><use href="#svg-moon"></use></svg>
|
||
<svg class="theme-icon-when-light"><use href="#svg-sun"></use></svg>
|
||
</button>
|
||
</div>
|
||
<label class="toc-overlay-icon toc-content-icon" for="__toc">
|
||
<div class="visually-hidden">Toggle table of contents sidebar</div>
|
||
<i class="icon"><svg><use href="#svg-toc"></use></svg></i>
|
||
</label>
|
||
</div>
|
||
<article role="main">
|
||
|
||
<section id="basic-usage">
|
||
<h1>Basic Usage<a class="headerlink" href="#basic-usage" title="Permalink to this heading">#</a></h1>
|
||
<p>Gymnasium is a project that provide an API for all single agent reinforcement learning environments that include implementations of common environments: cartpole, pendulum, mountain-car, mujoco, atari, and more.</p>
|
||
<p>The API contains four key functions: <code class="docutils literal notranslate"><span class="pre">make</span></code>, <code class="docutils literal notranslate"><span class="pre">reset</span></code>, <code class="docutils literal notranslate"><span class="pre">step</span></code> and <code class="docutils literal notranslate"><span class="pre">render</span></code> that this basic usage will introduce you to. At the core of Gymnasium is <code class="docutils literal notranslate"><span class="pre">Env</span></code> which is a high level python class representing a markov decision process from reinforcement learning theory (this is not a perfect reconstruction missing several components of MDPs). Within gymnasium, environments (MDPs) are implements as <code class="docutils literal notranslate"><span class="pre">Env</span></code> along with <code class="docutils literal notranslate"><span class="pre">Wrappers</span></code> that can change the results passed to the user.</p>
|
||
<section id="initializing-environments">
|
||
<h2>Initializing Environments<a class="headerlink" href="#initializing-environments" title="Permalink to this heading">#</a></h2>
|
||
<p>Initializing environments is very easy in Gymnasium and can be done via the <code class="docutils literal notranslate"><span class="pre">make</span></code> function:</p>
|
||
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="kn">import</span> <span class="nn">gymnasium</span> <span class="k">as</span> <span class="nn">gym</span>
|
||
<span class="n">env</span> <span class="o">=</span> <span class="n">gym</span><span class="o">.</span><span class="n">make</span><span class="p">(</span><span class="s1">'CartPole-v1'</span><span class="p">)</span>
|
||
</pre></div>
|
||
</div>
|
||
<p>This will return an <code class="docutils literal notranslate"><span class="pre">Env</span></code> for users to interact with. To see all environments you can create, use <code class="docutils literal notranslate"><span class="pre">gymnasium.envs.registry.keys()</span></code>.<code class="docutils literal notranslate"><span class="pre">make</span></code> includes a number of additional parameters to adding wrappers, specifying keywords to the environment and more.</p>
|
||
</section>
|
||
<section id="interacting-with-the-environment">
|
||
<h2>Interacting with the Environment<a class="headerlink" href="#interacting-with-the-environment" title="Permalink to this heading">#</a></h2>
|
||
<p>The classic “agent-environment loop” pictured below is simplified representation of reinforcement learning that Gymnasium implements.</p>
|
||
<a class="only-light reference internal image-reference" href="../../_images/AE_loop.png"><img alt="../../_images/AE_loop.png" class="only-light align-center" src="../../_images/AE_loop.png" style="width: 50%;" /></a>
|
||
<a class="only-dark reference internal image-reference" href="../../_images/AE_loop_dark.png"><img alt="../../_images/AE_loop_dark.png" class="only-dark align-center" src="../../_images/AE_loop_dark.png" style="width: 50%;" /></a>
|
||
<p>This loop is implemented using the following gymnasium code</p>
|
||
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="kn">import</span> <span class="nn">gymnasium</span> <span class="k">as</span> <span class="nn">gym</span>
|
||
<span class="n">env</span> <span class="o">=</span> <span class="n">gym</span><span class="o">.</span><span class="n">make</span><span class="p">(</span><span class="s2">"LunarLander-v2"</span><span class="p">,</span> <span class="n">render_mode</span><span class="o">=</span><span class="s2">"human"</span><span class="p">)</span>
|
||
<span class="n">observation</span><span class="p">,</span> <span class="n">info</span> <span class="o">=</span> <span class="n">env</span><span class="o">.</span><span class="n">reset</span><span class="p">()</span>
|
||
|
||
<span class="k">for</span> <span class="n">_</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="mi">1000</span><span class="p">):</span>
|
||
<span class="n">action</span> <span class="o">=</span> <span class="n">env</span><span class="o">.</span><span class="n">action_space</span><span class="o">.</span><span class="n">sample</span><span class="p">()</span> <span class="c1"># agent policy that uses the observation and info</span>
|
||
<span class="n">observation</span><span class="p">,</span> <span class="n">reward</span><span class="p">,</span> <span class="n">terminated</span><span class="p">,</span> <span class="n">truncated</span><span class="p">,</span> <span class="n">info</span> <span class="o">=</span> <span class="n">env</span><span class="o">.</span><span class="n">step</span><span class="p">(</span><span class="n">action</span><span class="p">)</span>
|
||
|
||
<span class="k">if</span> <span class="n">terminated</span> <span class="ow">or</span> <span class="n">truncated</span><span class="p">:</span>
|
||
<span class="n">observation</span><span class="p">,</span> <span class="n">info</span> <span class="o">=</span> <span class="n">env</span><span class="o">.</span><span class="n">reset</span><span class="p">()</span>
|
||
|
||
<span class="n">env</span><span class="o">.</span><span class="n">close</span><span class="p">()</span>
|
||
</pre></div>
|
||
</div>
|
||
<p>The output should look something like this:</p>
|
||
<figure class="align-center">
|
||
<a class="reference internal image-reference" href="https://user-images.githubusercontent.com/15806078/153222406-af5ce6f0-4696-4a24-a683-46ad4939170c.gif"><img alt="https://user-images.githubusercontent.com/15806078/153222406-af5ce6f0-4696-4a24-a683-46ad4939170c.gif" src="https://user-images.githubusercontent.com/15806078/153222406-af5ce6f0-4696-4a24-a683-46ad4939170c.gif" style="width: 50%;" /></a>
|
||
</figure>
|
||
<section id="explaining-the-code">
|
||
<h3>Explaining the code<a class="headerlink" href="#explaining-the-code" title="Permalink to this heading">#</a></h3>
|
||
<p>First, an environment is created using <code class="docutils literal notranslate"><span class="pre">make</span></code> with an additional keyword <code class="docutils literal notranslate"><span class="pre">"render_mode"</span></code> that specifies how the environment should be visualised. See <code class="docutils literal notranslate"><span class="pre">render</span></code> for details on the default meaning of different render modes. In this example, we use the <code class="docutils literal notranslate"><span class="pre">"LunarLander"</span></code> environment where the agent controls a spaceship that needs to land safely.</p>
|
||
<p>After initializing the environment, we <code class="docutils literal notranslate"><span class="pre">reset</span></code> the environment to get the first observation of the environment. For initializing the environment with a particular random seed or options (see environment documentation for possible values) use the <code class="docutils literal notranslate"><span class="pre">seed</span></code> or <code class="docutils literal notranslate"><span class="pre">options</span></code> parameters with <code class="docutils literal notranslate"><span class="pre">reset</span></code>.</p>
|
||
<p>Next, the agent performs an action in the environment, <code class="docutils literal notranslate"><span class="pre">step</span></code>, this can be imagined as moving a robot or pressing a button on a games’ controller that causes a change within the environment. As a result, the agent receives a new observation from the updated environment along with a reward for taking the action. This reward could be for instance positive for destroying an enemy or a negative reward for moving into lava. One such action-observation exchange is referred to as a <em>timestep</em>.</p>
|
||
<p>However, after some timesteps, the environment may end, this is called the terminal state. For instance, the robot may have crashed, or the agent have succeeded in completing a task, the environment will need to stop as the agent cannot continue. In gymnasium, if the environment has terminated, this is returned by <code class="docutils literal notranslate"><span class="pre">step</span></code>. Similarly, we may also want the environment to end after a fixed number of timesteps, in this case, the environment issues a truncated signal. If either of <code class="docutils literal notranslate"><span class="pre">terminated</span></code> or <code class="docutils literal notranslate"><span class="pre">truncated</span></code> are <code class="docutils literal notranslate"><span class="pre">true</span></code> then <code class="docutils literal notranslate"><span class="pre">reset</span></code> should be called next to restart the environment.</p>
|
||
</section>
|
||
</section>
|
||
<section id="action-and-observation-spaces">
|
||
<h2>Action and observation spaces<a class="headerlink" href="#action-and-observation-spaces" title="Permalink to this heading">#</a></h2>
|
||
<p>Every environment specifies the format of valid actions and observations with the <code class="docutils literal notranslate"><span class="pre">env.action_space</span></code> and <code class="docutils literal notranslate"><span class="pre">env.observation_space</span></code> attributes. This is helpful for both knowing the expected input and output of the environment as all valid actions and observation should be contained with the respective space.</p>
|
||
<p>In the example, we sampled random actions via <code class="docutils literal notranslate"><span class="pre">env.action_space.sample()</span></code> instead of using an agent policy, mapping observations to actions which users will want to make. See one of the agent tutorials for an example of creating and training an agent policy.</p>
|
||
<p>Every environment should have the attributes <code class="docutils literal notranslate"><span class="pre">action_space</span></code> and <code class="docutils literal notranslate"><span class="pre">observation_space</span></code>, both of which should be instances of classes that inherit from <code class="docutils literal notranslate"><span class="pre">Space</span></code>. Gymnasium has support for a major of possible spaces are users need:</p>
|
||
<ul class="simple">
|
||
<li><p><code class="docutils literal notranslate"><span class="pre">Box</span></code>: describes an n-dimensional continuous space. It’s a bounded space where we can define the upper and lower
|
||
limits which describe the valid values our observations can take.</p></li>
|
||
<li><p><code class="docutils literal notranslate"><span class="pre">Discrete</span></code>: describes a discrete space where {0, 1, …, n-1} are the possible values our observation or action can take.
|
||
Values can be shifted to {a, a+1, …, a+n-1} using an optional argument.</p></li>
|
||
<li><p><code class="docutils literal notranslate"><span class="pre">Dict</span></code>: represents a dictionary of simple spaces.</p></li>
|
||
<li><p><code class="docutils literal notranslate"><span class="pre">Tuple</span></code>: represents a tuple of simple spaces.</p></li>
|
||
<li><p><code class="docutils literal notranslate"><span class="pre">MultiBinary</span></code>: creates an n-shape binary space. Argument n can be a number or a list of numbers.</p></li>
|
||
<li><p><code class="docutils literal notranslate"><span class="pre">MultiDiscrete</span></code>: consists of a series of <code class="docutils literal notranslate"><span class="pre">Discrete</span></code> action spaces with a different number of actions in each element.</p></li>
|
||
</ul>
|
||
<p>For example usage of spaces, see their <a class="reference internal" href="../../api/spaces/"><span class="doc std std-doc">documentation</span></a> along with <a class="reference internal" href="../../api/spaces/utils/"><span class="doc std std-doc">utility functions</span></a>. There are a couple of more niche spaces <code class="docutils literal notranslate"><span class="pre">Graph</span></code>, <code class="docutils literal notranslate"><span class="pre">Sequence</span></code> and <code class="docutils literal notranslate"><span class="pre">Text</span></code>.</p>
|
||
</section>
|
||
<section id="modifying-the-environment">
|
||
<h2>Modifying the environment<a class="headerlink" href="#modifying-the-environment" title="Permalink to this heading">#</a></h2>
|
||
<p>Wrappers are a convenient way to modify an existing environment without having to alter the underlying code directly. Using wrappers will allow you to avoid a lot of boilerplate code and make your environment more modular. Wrappers can also be chained to combine their effects. Most environments that are generated via <code class="docutils literal notranslate"><span class="pre">gymnasium.make</span></code> will already be wrapped by default using the <code class="docutils literal notranslate"><span class="pre">TimeLimit</span></code>, <code class="docutils literal notranslate"><span class="pre">OrderEnforcing</span></code> and <code class="docutils literal notranslate"><span class="pre">PassiveEnvChecker</span></code>.</p>
|
||
<p>In order to wrap an environment, you must first initialize a base environment. Then you can pass this environment along with (possibly optional) parameters to the wrapper’s constructor:</p>
|
||
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="gp">>>> </span><span class="kn">import</span> <span class="nn">gymnasium</span>
|
||
<span class="gp">>>> </span><span class="kn">from</span> <span class="nn">gymnasium.wrappers</span> <span class="kn">import</span> <span class="n">RescaleAction</span>
|
||
<span class="gp">>>> </span><span class="n">base_env</span> <span class="o">=</span> <span class="n">gymnasium</span><span class="o">.</span><span class="n">make</span><span class="p">(</span><span class="s2">"BipedalWalker-v3"</span><span class="p">)</span>
|
||
<span class="gp">>>> </span><span class="n">base_env</span><span class="o">.</span><span class="n">action_space</span>
|
||
<span class="go">Box([-1. -1. -1. -1.], [1. 1. 1. 1.], (4,), float32)</span>
|
||
<span class="gp">>>> </span><span class="n">wrapped_env</span> <span class="o">=</span> <span class="n">RescaleAction</span><span class="p">(</span><span class="n">base_env</span><span class="p">,</span> <span class="n">min_action</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="n">max_action</span><span class="o">=</span><span class="mi">1</span><span class="p">)</span>
|
||
<span class="gp">>>> </span><span class="n">wrapped_env</span><span class="o">.</span><span class="n">action_space</span>
|
||
<span class="go">Box([0. 0. 0. 0.], [1. 1. 1. 1.], (4,), float32)</span>
|
||
</pre></div>
|
||
</div>
|
||
<p>Gymnasium already provides many commonly used wrappers for you. Some examples:</p>
|
||
<ul class="simple">
|
||
<li><p><code class="docutils literal notranslate"><span class="pre">TimeLimit</span></code>: Issue a truncated signal if a maximum number of timesteps has been exceeded (or the base environment has issued a truncated signal).</p></li>
|
||
<li><p><code class="docutils literal notranslate"><span class="pre">ClipAction</span></code>: Clip the action such that it lies in the action space (of type <code class="docutils literal notranslate"><span class="pre">Box</span></code>).</p></li>
|
||
<li><p><code class="docutils literal notranslate"><span class="pre">RescaleAction</span></code>: Rescale actions to lie in a specified interval</p></li>
|
||
<li><p><code class="docutils literal notranslate"><span class="pre">TimeAwareObservation</span></code>: Add information about the index of timestep to observation. In some cases helpful to ensure that transitions are Markov.</p></li>
|
||
</ul>
|
||
<p>For a full list of implemented wrappers in gymnasium, see <a class="reference internal" href="../../api/wrappers/"><span class="doc std std-doc">wrappers</span></a>.</p>
|
||
<p>If you have a wrapped environment, and you want to get the unwrapped environment underneath all the layers of wrappers (so that you can manually call a function or change some underlying aspect of the environment), you can use the <code class="docutils literal notranslate"><span class="pre">.unwrapped</span></code> attribute. If the environment is already a base environment, the <code class="docutils literal notranslate"><span class="pre">.unwrapped</span></code> attribute will just return itself.</p>
|
||
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="gp">>>> </span><span class="n">wrapped_env</span>
|
||
<span class="go"><RescaleAction<TimeLimit<BipedalWalker<BipedalWalker-v3>>>></span>
|
||
<span class="gp">>>> </span><span class="n">wrapped_env</span><span class="o">.</span><span class="n">unwrapped</span>
|
||
<span class="go"><gymnasium.envs.box2d.bipedal_walker.BipedalWalker object at 0x7f87d70712d0></span>
|
||
</pre></div>
|
||
</div>
|
||
</section>
|
||
<section id="more-information">
|
||
<h2>More information<a class="headerlink" href="#more-information" title="Permalink to this heading">#</a></h2>
|
||
<ul class="simple">
|
||
<li><p><a class="reference internal" href="../../tutorials/environment_creation/"><span class="doc std std-doc">Making a Custom environment using the Gymnasium API</span></a></p></li>
|
||
<li><p><a class="reference internal" href="../../tutorials/blackjack_tutorial/"><span class="doc std std-doc">Training an agent to play blackjack</span></a></p></li>
|
||
<li><p><a class="reference internal" href="../gym_compatibility/"><span class="doc std std-doc">Compatibility with OpenAI Gym</span></a></p></li>
|
||
</ul>
|
||
</section>
|
||
</section>
|
||
|
||
</article>
|
||
</div>
|
||
<footer>
|
||
|
||
<div class="related-pages">
|
||
<a class="next-page" href="../gym_compatibility/">
|
||
<div class="page-info">
|
||
<div class="context">
|
||
<span>Next</span>
|
||
</div>
|
||
<div class="title">Compatibility with Gym</div>
|
||
</div>
|
||
<svg class="furo-related-icon"><use href="#svg-arrow-right"></use></svg>
|
||
</a>
|
||
|
||
</div>
|
||
<div class="bottom-of-page">
|
||
<div class="left-details">
|
||
<div class="copyright">
|
||
Copyright © 2022 Farama Foundation
|
||
</div>
|
||
<!--
|
||
Made with <a href="https://www.sphinx-doc.org/">Sphinx</a> and <a class="muted-link" href="https://pradyunsg.me">@pradyunsg</a>'s
|
||
|
||
<a href="https://github.com/pradyunsg/furo">Furo</a>
|
||
-->
|
||
</div>
|
||
<div class="right-details">
|
||
<div class="icons">
|
||
|
||
</div>
|
||
</div>
|
||
</div>
|
||
|
||
</footer>
|
||
</div>
|
||
<aside class="toc-drawer">
|
||
|
||
|
||
<div class="toc-sticky toc-scroll">
|
||
<div class="toc-title-container">
|
||
<span class="toc-title">
|
||
On this page
|
||
</span>
|
||
</div>
|
||
<div class="toc-tree-container">
|
||
<div class="toc-tree">
|
||
<ul>
|
||
<li><a class="reference internal" href="#">Basic Usage</a><ul>
|
||
<li><a class="reference internal" href="#initializing-environments">Initializing Environments</a></li>
|
||
<li><a class="reference internal" href="#interacting-with-the-environment">Interacting with the Environment</a><ul>
|
||
<li><a class="reference internal" href="#explaining-the-code">Explaining the code</a></li>
|
||
</ul>
|
||
</li>
|
||
<li><a class="reference internal" href="#action-and-observation-spaces">Action and observation spaces</a></li>
|
||
<li><a class="reference internal" href="#modifying-the-environment">Modifying the environment</a></li>
|
||
<li><a class="reference internal" href="#more-information">More information</a></li>
|
||
</ul>
|
||
</li>
|
||
</ul>
|
||
|
||
</div>
|
||
</div>
|
||
</div>
|
||
|
||
|
||
</aside>
|
||
</div>
|
||
</div>
|
||
<script>
|
||
let toggleMenu = () => {
|
||
document.querySelector(".farama-header-menu").classList.toggle("active");
|
||
document.querySelector(".farama-header-menu__overlay").classList.toggle("active");
|
||
}
|
||
|
||
document.querySelector(".farama-header-menu__btn").addEventListener("click", toggleMenu);
|
||
document.getElementById("farama-close-menu").addEventListener("click", toggleMenu);
|
||
document.querySelector(".farama-header-menu__overlay").addEventListener("click", toggleMenu);
|
||
|
||
window.onclick = function(event) {
|
||
if (!event.target.matches('.farama-header-menu__btn')) {
|
||
const dropdown = document.querySelector(".farama-header-menu-container");
|
||
if (dropdown.classList.contains('active')) {
|
||
dropdown.classList.remove('active');
|
||
document.querySelector(".farama-header-menu__overlay").classList.remove("active");
|
||
}
|
||
}
|
||
}
|
||
</script>
|
||
|
||
|
||
<script>
|
||
(() => {
|
||
if (!localStorage.getItem("shownCookieAlert")) {
|
||
const boxElem = document.createElement("div");
|
||
boxElem.classList.add("cookie-alert");
|
||
const containerElem = document.createElement("div");
|
||
containerElem.classList.add("cookie-alert__container");
|
||
const textElem = document.createElement("p");
|
||
textElem.innerHTML = `This page uses <a href="https://analytics.google.com/">
|
||
Google Analytics</a> to collect statistics. You can disable it by blocking
|
||
the JavaScript coming from www.google-analytics.com.`;
|
||
containerElem.appendChild(textElem);
|
||
const closeBtn = document.createElement("button");
|
||
closeBtn.innerHTML = `<?xml version="1.0" ?><svg viewBox="0 0 32 32" xmlns="http://www.w3.org/2000/svg"><defs><style>.cls-1{fill:none;stroke:#000;stroke-linecap:round;stroke-linejoin:round;stroke-width:2px;}</style></defs><title/><g id="cross"><line class="cls-1" x1="7" x2="25" y1="7" y2="25"/><line class="cls-1" x1="7" x2="25" y1="25" y2="7"/></g></svg>`
|
||
closeBtn.onclick = () => {
|
||
localStorage.setItem("shownCookieAlert", "true");
|
||
boxElem.style.display = "none";
|
||
}
|
||
containerElem.appendChild(closeBtn);
|
||
boxElem.appendChild(containerElem);
|
||
document.body.appendChild(boxElem);
|
||
}
|
||
})()
|
||
</script>
|
||
|
||
<script async src="https://www.googletagmanager.com/gtag/js?id=G-6H9C8TWXZ8"></script>
|
||
<script>
|
||
window.dataLayer = window.dataLayer || [];
|
||
function gtag(){dataLayer.push(arguments);}
|
||
gtag('js', new Date());
|
||
|
||
gtag('config', 'G-6H9C8TWXZ8');
|
||
</script>
|
||
|
||
<script data-url_root="../../" id="documentation_options" src="../../_static/documentation_options.js"></script>
|
||
<script src="../../_static/jquery.js"></script>
|
||
<script src="../../_static/underscore.js"></script>
|
||
<script src="../../_static/_sphinx_javascript_frameworks_compat.js"></script>
|
||
<script src="../../_static/doctools.js"></script>
|
||
<script src="../../_static/sphinx_highlight.js"></script>
|
||
<script src="../../_static/scripts/furo.js"></script>
|
||
|
||
<script>
|
||
const versioningConfig = {
|
||
githubUser: 'Farama-Foundation',
|
||
githubRepo: 'Gymnasium',
|
||
};
|
||
fetch('/_static/versioning/versioning_menu.html').then(response => {
|
||
if (response.status === 200) {
|
||
response.text().then(text => {
|
||
const container = document.createElement("div");
|
||
container.innerHTML = text;
|
||
document.querySelector("body").appendChild(container);
|
||
// innerHtml doenst evaluate scripts, we need to add them dynamically
|
||
Array.from(container.querySelectorAll("script")).forEach(oldScript => {
|
||
const newScript = document.createElement("script");
|
||
Array.from(oldScript.attributes).forEach(attr => newScript.setAttribute(attr.name, attr.value));
|
||
newScript.appendChild(document.createTextNode(oldScript.innerHTML));
|
||
oldScript.parentNode.replaceChild(newScript, oldScript);
|
||
});
|
||
});
|
||
} else {
|
||
console.warn("Unable to load versioning menu", response);
|
||
}
|
||
});
|
||
</script></body>
|
||
</html> |