mirror of
https://github.com/Farama-Foundation/Gymnasium.git
synced 2025-08-19 21:42:02 +00:00
945 lines
57 KiB
HTML
945 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/environments/classic_control/acrobot.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="Cart Pole" href="../cart_pole/" /><link rel="prev" title="Classic Control" href="../" />
|
|||
|
<link rel="canonical" href="https://gymnasium.farama.org/environments/classic_control/acrobot.html" />
|
|||
|
|
|||
|
<link rel="shortcut icon" href="../../../_static/favicon.png"/><!-- Generated with Sphinx 6.1.3 and Furo 2022.12.07.dev1 -->
|
|||
|
<title>Acrobot - 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=721f65a87c37740baa8d605b09db5bec3a2987a8" />
|
|||
|
<link rel="stylesheet" type="text/css" href="../../../_static/sg_gallery.css" />
|
|||
|
<link rel="stylesheet" type="text/css" href="../../../_static/sg_gallery-binder.css" />
|
|||
|
<link rel="stylesheet" type="text/css" href="../../../_static/sg_gallery-dataframe.css" />
|
|||
|
<link rel="stylesheet" type="text/css" href="../../../_static/sg_gallery-rendered-html.css" />
|
|||
|
<link rel="stylesheet" type="text/css" href="../../../_static/styles/furo-extensions.css?digest=b0c92cd440df7c18a0306b0433406327ff2c572f" />
|
|||
|
|
|||
|
|
|||
|
|
|||
|
|
|||
|
<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" aria-label="Farama header">
|
|||
|
<div class="farama-header__container">
|
|||
|
<div class="farama-header__left--mobile">
|
|||
|
<label class="nav-overlay-icon" for="__navigation">
|
|||
|
<div class="visually-hidden">Toggle site navigation sidebar</div>
|
|||
|
<svg viewBox="0 0 24 24" xmlns="http://www.w3.org/2000/svg">
|
|||
|
<defs></defs>
|
|||
|
<line x1="0.5" y1="4" x2="23.5" y2="4"></line>
|
|||
|
<line x1="0.232" y1="12" x2="23.5" y2="12"></line>
|
|||
|
<line x1="0.232" y1="20" x2="23.5" y2="20"></line>
|
|||
|
</svg>
|
|||
|
<!-- <svg viewBox="0 0 24 24" viewBox="0 0 24 24" xmlns="http://www.w3.org/2000/svg">
|
|||
|
<line x1="0.5" y1="4.5" x2="23.5" y2="4.5" style="fill: none; "></line>
|
|||
|
<line x1="0.5" y1="12" x2="14" y2="12" ></line>
|
|||
|
<line x1="0.5" y1="19.5" x2="23.5" y2="19.5"></line>
|
|||
|
<polyline style="stroke-width: 0px;" points="17 7 22 12 17 17"></polyline>
|
|||
|
</svg> -->
|
|||
|
<!-- <svg viewBox="0 0 24 24" xmlns="http://www.w3.org/2000/svg" style="width:20px">
|
|||
|
<defs></defs>
|
|||
|
<rect y="1" width="22" height="22" rx="2" ry="2" style="fill: none;" x="1"></rect>
|
|||
|
<line x1="8" y1="1" x2="8" y2="23"></line>
|
|||
|
<polyline style="stroke-linecap: round; fill: none; stroke-linejoin: round;" points="13 7 17 12 13 17"></polyline>
|
|||
|
</svg> -->
|
|||
|
</label>
|
|||
|
</div>
|
|||
|
<div class="farama-header__left farama-header__center--mobile">
|
|||
|
<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"/>
|
|||
|
<span class="farama-header__title">Gymnasium Documentation</span>
|
|||
|
</a>
|
|||
|
</div>
|
|||
|
<div class="farama-header__right">
|
|||
|
<div class="farama-header-menu">
|
|||
|
<button class="farama-header-menu__btn" aria-label="Open Farama Menu" aria-expanded="false" aria-haspopup="true" aria-controls="farama-menu">
|
|||
|
<img class="farama-black-logo-invert" src="../../../_static/img/farama-logo-header.svg">
|
|||
|
<svg viewBox="0 0 24 24" viewBox="0 0 24 24" xmlns="http://www.w3.org/2000/svg">
|
|||
|
<polyline style="stroke-linecap: round; stroke-linejoin: round; fill: none; stroke-width: 2px;" points="1 7 12 18 23 7"></polyline>
|
|||
|
</svg>
|
|||
|
</button>
|
|||
|
<div class="farama-header-menu-container farama-hidden" aria-hidden="true" id="farama-menu">
|
|||
|
<div class="farama-header-menu__header">
|
|||
|
<a href="https://farama.org">
|
|||
|
<img class="farama-header-menu__logo farama-white-logo-invert" src="../../../_static/img/farama_solid_white.svg" alt="Farama Foundation logo">
|
|||
|
<span>Farama Foundation</span>
|
|||
|
</a>
|
|||
|
<div class="farama-header-menu-header__right">
|
|||
|
<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>
|
|||
|
<div class="farama-header-menu__body">
|
|||
|
<!-- Response from farama.org/api/projects.json -->
|
|||
|
</div>
|
|||
|
</div>
|
|||
|
</div>
|
|||
|
</div>
|
|||
|
</div>
|
|||
|
</header>
|
|||
|
|
|||
|
|
|||
|
<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"><a class="farama-sidebar__title" 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"/>
|
|||
|
<span class="farama-header__title">Gymnasium Documentation</span>
|
|||
|
</a><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>
|
|||
|
<li class="toctree-l1"><a class="reference internal" href="../../../content/basic_usage/">Basic Usage</a></li>
|
|||
|
<li class="toctree-l1"><a class="reference internal" href="../../../content/gym_compatibility/">Compatibility with Gym</a></li>
|
|||
|
<li class="toctree-l1"><a class="reference internal" href="../../../content/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/">Register and Make</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>
|
|||
|
<li class="toctree-l1 has-children"><a class="reference internal" href="../../../api/experimental/">Experimental</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="../../../api/experimental/functional/">Functional Environment</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../../api/experimental/wrappers/">Wrappers</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../../api/experimental/vector/">Vectorizing Environment</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../../api/experimental/vector_wrappers/">Vector Environment Wrappers</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../../api/experimental/vector_utils/">Utility functions for vectorisation</a></li>
|
|||
|
</ul>
|
|||
|
</li>
|
|||
|
</ul>
|
|||
|
<p class="caption" role="heading"><span class="caption-text">Environments</span></p>
|
|||
|
<ul class="current">
|
|||
|
<li class="toctree-l1 current has-children"><a class="reference internal" href="../">Classic Control</a><input checked="" 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 class="current">
|
|||
|
<li class="toctree-l2 current current-page"><a class="current reference internal" href="#">Acrobot</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../cart_pole/">Cart Pole</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../mountain_car_continuous/">Mountain Car Continuous</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../mountain_car/">Mountain Car</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../pendulum/">Pendulum</a></li>
|
|||
|
</ul>
|
|||
|
</li>
|
|||
|
<li class="toctree-l1 has-children"><a class="reference internal" href="../../box2d/">Box2D</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="../../box2d/bipedal_walker/">Bipedal Walker</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../box2d/car_racing/">Car Racing</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../box2d/lunar_lander/">Lunar Lander</a></li>
|
|||
|
</ul>
|
|||
|
</li>
|
|||
|
<li class="toctree-l1 has-children"><a class="reference internal" href="../../toy_text/">Toy Text</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="../../toy_text/blackjack/">Blackjack</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../toy_text/taxi/">Taxi</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../toy_text/cliff_walking/">Cliff Walking</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../toy_text/frozen_lake/">Frozen Lake</a></li>
|
|||
|
</ul>
|
|||
|
</li>
|
|||
|
<li class="toctree-l1 has-children"><a class="reference internal" href="../../mujoco/">MuJoCo</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="../../mujoco/ant/">Ant</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../mujoco/half_cheetah/">Half Cheetah</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../mujoco/hopper/">Hopper</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../mujoco/humanoid_standup/">Humanoid Standup</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../mujoco/humanoid/">Humanoid</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../mujoco/inverted_double_pendulum/">Inverted Double Pendulum</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../mujoco/inverted_pendulum/">Inverted Pendulum</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../mujoco/reacher/">Reacher</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../mujoco/swimmer/">Swimmer</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../mujoco/pusher/">Pusher</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../mujoco/walker2d/">Walker2D</a></li>
|
|||
|
</ul>
|
|||
|
</li>
|
|||
|
<li class="toctree-l1 has-children"><a class="reference internal" href="../../atari/">Atari</a><input class="toctree-checkbox" id="toctree-checkbox-8" name="toctree-checkbox-8" role="switch" type="checkbox"/><label for="toctree-checkbox-8"><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="../../atari/adventure/">Adventure</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/air_raid/">AirRaid</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/alien/">Alien</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/amidar/">Amidar</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/assault/">Assault</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/asterix/">Asterix</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/asteroids/">Asteroids</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/atlantis/">Atlantis</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/atlantis2/">Atlantis2</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/backgammon/">Backgammon</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/bank_heist/">BankHeist</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/basic_math/">BasicMath</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/battle_zone/">BattleZone</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/beam_rider/">BeamRider</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/berzerk/">Berzerk</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/blackjack/">Blackjack</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/bowling/">Bowling</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/boxing/">Boxing</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/breakout/">Breakout</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/carnival/">Carnival</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/casino/">Casino</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/centipede/">Centipede</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/chopper_command/">ChopperCommand</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/crazy_climber/">CrazyClimber</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/crossbow/">Crossbow</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/darkchambers/">Darkchambers</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/defender/">Defender</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/demon_attack/">DemonAttack</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/donkey_kong/">DonkeyKong</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/double_dunk/">DoubleDunk</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/earthworld/">Earthworld</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/elevator_action/">ElevatorAction</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/enduro/">Enduro</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/entombed/">Entombed</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/et/">Et</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/fishing_derby/">FishingDerby</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/flag_capture/">FlagCapture</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/freeway/">Freeway</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/frogger/">Frogger</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/frostbite/">Frostbite</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/galaxian/">Galaxian</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/gopher/">Gopher</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/gravitar/">Gravitar</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/hangman/">Hangman</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/haunted_house/">HauntedHouse</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/hero/">Hero</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/human_cannonball/">HumanCannonball</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/ice_hockey/">IceHockey</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/jamesbond/">Jamesbond</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/journey_escape/">JourneyEscape</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/kaboom/">Kaboom</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/kangaroo/">Kangaroo</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/keystone_kapers/">KeystoneKapers</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/king_kong/">KingKong</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/klax/">Klax</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/koolaid/">Koolaid</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/krull/">Krull</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/kung_fu_master/">KungFuMaster</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/laser_gates/">LaserGates</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/lost_luggage/">LostLuggage</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/mario_bros/">MarioBros</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/miniature_golf/">MiniatureGolf</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/montezuma_revenge/">MontezumaRevenge</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/mr_do/">MrDo</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/ms_pacman/">MsPacman</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/name_this_game/">NameThisGame</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/othello/">Othello</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/pacman/">Pacman</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/phoenix/">Phoenix</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/pitfall/">Pitfall</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/pitfall2/">Pitfall2</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/pong/">Pong</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/pooyan/">Pooyan</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/private_eye/">PrivateEye</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/qbert/">Qbert</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/riverraid/">Riverraid</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/road_runner/">RoadRunner</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/robotank/">Robotank</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/seaquest/">Seaquest</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/sir_lancelot/">SirLancelot</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/skiing/">Skiing</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/solaris/">Solaris</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/space_invaders/">SpaceInvaders</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/space_war/">SpaceWar</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/star_gunner/">StarGunner</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/superman/">Superman</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/surround/">Surround</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/tennis/">Tennis</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/tetris/">Tetris</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/tic_tac_toe_3d/">TicTacToe3D</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/time_pilot/">TimePilot</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/trondead/">Trondead</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/turmoil/">Turmoil</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/tutankham/">Tutankham</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/up_n_down/">UpNDown</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/venture/">Venture</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/video_checkers/">VideoCheckers</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/video_chess/">VideoChess</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/video_cube/">VideoCube</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/video_pinball/">VideoPinball</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/wizard_of_wor/">WizardOfWor</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/word_zapper/">WordZapper</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/yars_revenge/">YarsRevenge</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/zaxxon/">Zaxxon</a></li>
|
|||
|
</ul>
|
|||
|
</li>
|
|||
|
<li class="toctree-l1"><a class="reference internal" href="../../third_party_environments/">Third-Party Environments</a></li>
|
|||
|
<li class="toctree-l1"><a class="reference internal" href="../../third_party_environments/#third-party-environments-using-gym">Third-Party Environments using Gym</a></li>
|
|||
|
</ul>
|
|||
|
<p class="caption" role="heading"><span class="caption-text">Tutorials</span></p>
|
|||
|
<ul>
|
|||
|
<li class="toctree-l1 has-children"><a class="reference internal" href="../../../tutorials/gymnasium_basics/">Gymnasium Basics</a><input class="toctree-checkbox" id="toctree-checkbox-9" name="toctree-checkbox-9" role="switch" type="checkbox"/><label for="toctree-checkbox-9"><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="../../../tutorials/gymnasium_basics/handling_time_limits/">Handling Time Limits</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../../tutorials/gymnasium_basics/implementing_custom_wrappers/">Implementing Custom Wrappers</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../../tutorials/gymnasium_basics/environment_creation/">Make your own custom environment</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../../tutorials/gymnasium_basics/vector_envs_tutorial/">Training A2C with Vector Envs and Domain Randomization</a></li>
|
|||
|
</ul>
|
|||
|
</li>
|
|||
|
<li class="toctree-l1 has-children"><a class="reference internal" href="../../../tutorials/training_agents/">Training Agents</a><input class="toctree-checkbox" id="toctree-checkbox-10" name="toctree-checkbox-10" role="switch" type="checkbox"/><label for="toctree-checkbox-10"><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="../../../tutorials/training_agents/reinforce_invpend_gym_v26/">Training using REINFORCE for Mujoco</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../../tutorials/training_agents/blackjack_tutorial/">Solving Blackjack with Q-Learning</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../../tutorials/training_agents/FrozenLake_tuto/">Frozenlake benchmark</a></li>
|
|||
|
</ul>
|
|||
|
</li>
|
|||
|
<li class="toctree-l1"><a class="reference external" href="https://www.comet.com/docs/v2/integrations/ml-frameworks/gymnasium/?utm_source=gymnasium&utm_medium=partner&utm_campaign=partner_gymnasium_2023&utm_content=docs_gymnasium">Comet Tutorial</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 internal" href="../../../gymnasium_release_notes/">Gymnasium Release Notes</a></li>
|
|||
|
<li class="toctree-l1"><a class="reference internal" href="../../../gym_release_notes/">Gym Release Notes</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-container">
|
|||
|
|
|||
|
|
|||
|
|
|||
|
|
|||
|
|
|||
|
<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="theme-toggle-container theme-toggle-content">
|
|||
|
<button class="theme-toggle" title="Toggle color theme">
|
|||
|
<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="acrobot">
|
|||
|
<h1>Acrobot<a class="headerlink" href="#acrobot" title="Permalink to this heading">#</a></h1>
|
|||
|
<figure class="align-default" id="id1">
|
|||
|
<a class="reference internal image-reference" href="../../../_images/acrobot.gif"><img alt="../../../_images/acrobot.gif" src="../../../_images/acrobot.gif" style="width: 200px;" /></a>
|
|||
|
</figure>
|
|||
|
<p>This environment is part of the Classic Control environments which contains general information about the environment.</p>
|
|||
|
<div class="table-wrapper colwidths-auto docutils container">
|
|||
|
<table class="docutils align-default">
|
|||
|
<thead>
|
|||
|
<tr class="row-odd"><th class="head"><p></p></th>
|
|||
|
<th class="head"><p></p></th>
|
|||
|
</tr>
|
|||
|
</thead>
|
|||
|
<tbody>
|
|||
|
<tr class="row-even"><td><p>Action Space</p></td>
|
|||
|
<td><p><code class="docutils literal notranslate"><span class="pre">Discrete(3)</span></code></p></td>
|
|||
|
</tr>
|
|||
|
<tr class="row-odd"><td><p>Observation Space</p></td>
|
|||
|
<td><p><code class="docutils literal notranslate"><span class="pre">Box([</span> <span class="pre">-1.</span> <span class="pre">-1.</span> <span class="pre">-1.</span> <span class="pre">-1.</span> <span class="pre">-12.566371</span> <span class="pre">-28.274334],</span> <span class="pre">[</span> <span class="pre">1.</span> <span class="pre">1.</span> <span class="pre">1.</span> <span class="pre">1.</span> <span class="pre">12.566371</span> <span class="pre">28.274334],</span> <span class="pre">(6,),</span> <span class="pre">float32)</span></code></p></td>
|
|||
|
</tr>
|
|||
|
<tr class="row-even"><td><p>import</p></td>
|
|||
|
<td><p><code class="docutils literal notranslate"><span class="pre">gymnasium.make("Acrobot-v1")</span></code></p></td>
|
|||
|
</tr>
|
|||
|
</tbody>
|
|||
|
</table>
|
|||
|
</div>
|
|||
|
<section id="description">
|
|||
|
<h2>Description<a class="headerlink" href="#description" title="Permalink to this heading">#</a></h2>
|
|||
|
<p>The Acrobot environment is based on Sutton’s work in
|
|||
|
<a class="reference external" href="https://papers.nips.cc/paper/1995/hash/8f1d43620bc6bb580df6e80b0dc05c48-Abstract.html">“Generalization in Reinforcement Learning: Successful Examples Using Sparse Coarse Coding”</a>
|
|||
|
and <a class="reference external" href="http://www.incompleteideas.net/book/the-book-2nd.html">Sutton and Barto’s book</a>.
|
|||
|
The system consists of two links connected linearly to form a chain, with one end of
|
|||
|
the chain fixed. The joint between the two links is actuated. The goal is to apply
|
|||
|
torques on the actuated joint to swing the free end of the linear chain above a
|
|||
|
given height while starting from the initial state of hanging downwards.</p>
|
|||
|
<p>As seen in the <strong>Gif</strong>: two blue links connected by two green joints. The joint in
|
|||
|
between the two links is actuated. The goal is to swing the free end of the outer-link
|
|||
|
to reach the target height (black horizontal line above system) by applying torque on
|
|||
|
the actuator.</p>
|
|||
|
</section>
|
|||
|
<section id="action-space">
|
|||
|
<h2>Action Space<a class="headerlink" href="#action-space" title="Permalink to this heading">#</a></h2>
|
|||
|
<p>The action is discrete, deterministic, and represents the torque applied on the actuated
|
|||
|
joint between the two links.</p>
|
|||
|
<div class="table-wrapper colwidths-auto docutils container">
|
|||
|
<table class="docutils align-default">
|
|||
|
<thead>
|
|||
|
<tr class="row-odd"><th class="head"><p>Num</p></th>
|
|||
|
<th class="head"><p>Action</p></th>
|
|||
|
<th class="head"><p>Unit</p></th>
|
|||
|
</tr>
|
|||
|
</thead>
|
|||
|
<tbody>
|
|||
|
<tr class="row-even"><td><p>0</p></td>
|
|||
|
<td><p>apply -1 torque to the actuated joint</p></td>
|
|||
|
<td><p>torque (N m)</p></td>
|
|||
|
</tr>
|
|||
|
<tr class="row-odd"><td><p>1</p></td>
|
|||
|
<td><p>apply 0 torque to the actuated joint</p></td>
|
|||
|
<td><p>torque (N m)</p></td>
|
|||
|
</tr>
|
|||
|
<tr class="row-even"><td><p>2</p></td>
|
|||
|
<td><p>apply 1 torque to the actuated joint</p></td>
|
|||
|
<td><p>torque (N m)</p></td>
|
|||
|
</tr>
|
|||
|
</tbody>
|
|||
|
</table>
|
|||
|
</div>
|
|||
|
</section>
|
|||
|
<section id="observation-space">
|
|||
|
<h2>Observation Space<a class="headerlink" href="#observation-space" title="Permalink to this heading">#</a></h2>
|
|||
|
<p>The observation is a <code class="docutils literal notranslate"><span class="pre">ndarray</span></code> with shape <code class="docutils literal notranslate"><span class="pre">(6,)</span></code> that provides information about the
|
|||
|
two rotational joint angles as well as their angular velocities:</p>
|
|||
|
<div class="table-wrapper colwidths-auto docutils container">
|
|||
|
<table class="docutils align-default">
|
|||
|
<thead>
|
|||
|
<tr class="row-odd"><th class="head"><p>Num</p></th>
|
|||
|
<th class="head"><p>Observation</p></th>
|
|||
|
<th class="head"><p>Min</p></th>
|
|||
|
<th class="head"><p>Max</p></th>
|
|||
|
</tr>
|
|||
|
</thead>
|
|||
|
<tbody>
|
|||
|
<tr class="row-even"><td><p>0</p></td>
|
|||
|
<td><p>Cosine of <code class="docutils literal notranslate"><span class="pre">theta1</span></code></p></td>
|
|||
|
<td><p>-1</p></td>
|
|||
|
<td><p>1</p></td>
|
|||
|
</tr>
|
|||
|
<tr class="row-odd"><td><p>1</p></td>
|
|||
|
<td><p>Sine of <code class="docutils literal notranslate"><span class="pre">theta1</span></code></p></td>
|
|||
|
<td><p>-1</p></td>
|
|||
|
<td><p>1</p></td>
|
|||
|
</tr>
|
|||
|
<tr class="row-even"><td><p>2</p></td>
|
|||
|
<td><p>Cosine of <code class="docutils literal notranslate"><span class="pre">theta2</span></code></p></td>
|
|||
|
<td><p>-1</p></td>
|
|||
|
<td><p>1</p></td>
|
|||
|
</tr>
|
|||
|
<tr class="row-odd"><td><p>3</p></td>
|
|||
|
<td><p>Sine of <code class="docutils literal notranslate"><span class="pre">theta2</span></code></p></td>
|
|||
|
<td><p>-1</p></td>
|
|||
|
<td><p>1</p></td>
|
|||
|
</tr>
|
|||
|
<tr class="row-even"><td><p>4</p></td>
|
|||
|
<td><p>Angular velocity of <code class="docutils literal notranslate"><span class="pre">theta1</span></code></p></td>
|
|||
|
<td><p>~ -12.567 (-4 * pi)</p></td>
|
|||
|
<td><p>~ 12.567 (4 * pi)</p></td>
|
|||
|
</tr>
|
|||
|
<tr class="row-odd"><td><p>5</p></td>
|
|||
|
<td><p>Angular velocity of <code class="docutils literal notranslate"><span class="pre">theta2</span></code></p></td>
|
|||
|
<td><p>~ -28.274 (-9 * pi)</p></td>
|
|||
|
<td><p>~ 28.274 (9 * pi)</p></td>
|
|||
|
</tr>
|
|||
|
</tbody>
|
|||
|
</table>
|
|||
|
</div>
|
|||
|
<p>where</p>
|
|||
|
<ul class="simple">
|
|||
|
<li><p><code class="docutils literal notranslate"><span class="pre">theta1</span></code> is the angle of the first joint, where an angle of 0 indicates the first link is pointing directly
|
|||
|
downwards.</p></li>
|
|||
|
<li><p><code class="docutils literal notranslate"><span class="pre">theta2</span></code> is <em><strong>relative to the angle of the first link.</strong></em>
|
|||
|
An angle of 0 corresponds to having the same angle between the two links.</p></li>
|
|||
|
</ul>
|
|||
|
<p>The angular velocities of <code class="docutils literal notranslate"><span class="pre">theta1</span></code> and <code class="docutils literal notranslate"><span class="pre">theta2</span></code> are bounded at ±4π, and ±9π rad/s respectively.
|
|||
|
A state of <code class="docutils literal notranslate"><span class="pre">[1,</span> <span class="pre">0,</span> <span class="pre">1,</span> <span class="pre">0,</span> <span class="pre">...,</span> <span class="pre">...]</span></code> indicates that both links are pointing downwards.</p>
|
|||
|
</section>
|
|||
|
<section id="rewards">
|
|||
|
<h2>Rewards<a class="headerlink" href="#rewards" title="Permalink to this heading">#</a></h2>
|
|||
|
<p>The goal is to have the free end reach a designated target height in as few steps as possible,
|
|||
|
and as such all steps that do not reach the goal incur a reward of -1.
|
|||
|
Achieving the target height results in termination with a reward of 0. The reward threshold is -100.</p>
|
|||
|
</section>
|
|||
|
<section id="starting-state">
|
|||
|
<h2>Starting State<a class="headerlink" href="#starting-state" title="Permalink to this heading">#</a></h2>
|
|||
|
<p>Each parameter in the underlying state (<code class="docutils literal notranslate"><span class="pre">theta1</span></code>, <code class="docutils literal notranslate"><span class="pre">theta2</span></code>, and the two angular velocities) is initialized
|
|||
|
uniformly between -0.1 and 0.1. This means both links are pointing downwards with some initial stochasticity.</p>
|
|||
|
</section>
|
|||
|
<section id="episode-end">
|
|||
|
<h2>Episode End<a class="headerlink" href="#episode-end" title="Permalink to this heading">#</a></h2>
|
|||
|
<p>The episode ends if one of the following occurs:</p>
|
|||
|
<ol class="arabic simple">
|
|||
|
<li><p>Termination: The free end reaches the target height, which is constructed as:
|
|||
|
<code class="docutils literal notranslate"><span class="pre">-cos(theta1)</span> <span class="pre">-</span> <span class="pre">cos(theta2</span> <span class="pre">+</span> <span class="pre">theta1)</span> <span class="pre">></span> <span class="pre">1.0</span></code></p></li>
|
|||
|
<li><p>Truncation: Episode length is greater than 500 (200 for v0)</p></li>
|
|||
|
</ol>
|
|||
|
</section>
|
|||
|
<section id="arguments">
|
|||
|
<h2>Arguments<a class="headerlink" href="#arguments" title="Permalink to this heading">#</a></h2>
|
|||
|
<p>No additional arguments are currently supported during construction.</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">'Acrobot-v1'</span><span class="p">)</span>
|
|||
|
</pre></div>
|
|||
|
</div>
|
|||
|
<p>On reset, the <code class="docutils literal notranslate"><span class="pre">options</span></code> parameter allows the user to change the bounds used to determine
|
|||
|
the new random state.</p>
|
|||
|
<p>By default, the dynamics of the acrobot follow those described in Sutton and Barto’s book
|
|||
|
<a class="reference external" href="http://incompleteideas.net/book/11/node4.html">Reinforcement Learning: An Introduction</a>.
|
|||
|
However, a <code class="docutils literal notranslate"><span class="pre">book_or_nips</span></code> parameter can be modified to change the pendulum dynamics to those described
|
|||
|
in the original <a class="reference external" href="https://papers.nips.cc/paper/1995/hash/8f1d43620bc6bb580df6e80b0dc05c48-Abstract.html">NeurIPS paper</a>.</p>
|
|||
|
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="c1"># To change the dynamics as described above</span>
|
|||
|
<span class="n">env</span><span class="o">.</span><span class="n">unwrapped</span><span class="o">.</span><span class="n">book_or_nips</span> <span class="o">=</span> <span class="s1">'nips'</span>
|
|||
|
</pre></div>
|
|||
|
</div>
|
|||
|
<p>See the following note for details:</p>
|
|||
|
<blockquote>
|
|||
|
<div><p>The dynamics equations were missing some terms in the NIPS paper which
|
|||
|
are present in the book. R. Sutton confirmed in personal correspondence
|
|||
|
that the experimental results shown in the paper and the book were
|
|||
|
generated with the equations shown in the book.
|
|||
|
However, there is the option to run the domain with the paper equations
|
|||
|
by setting <code class="docutils literal notranslate"><span class="pre">book_or_nips</span> <span class="pre">=</span> <span class="pre">'nips'</span></code></p>
|
|||
|
</div></blockquote>
|
|||
|
</section>
|
|||
|
<section id="version-history">
|
|||
|
<h2>Version History<a class="headerlink" href="#version-history" title="Permalink to this heading">#</a></h2>
|
|||
|
<ul class="simple">
|
|||
|
<li><p>v1: Maximum number of steps increased from 200 to 500. The observation space for v0 provided direct readings of
|
|||
|
<code class="docutils literal notranslate"><span class="pre">theta1</span></code> and <code class="docutils literal notranslate"><span class="pre">theta2</span></code> in radians, having a range of <code class="docutils literal notranslate"><span class="pre">[-pi,</span> <span class="pre">pi]</span></code>. The v1 observation space as described here provides the
|
|||
|
sine and cosine of each angle instead.</p></li>
|
|||
|
<li><p>v0: Initial versions release (1.0.0) (removed from gymnasium for v1)</p></li>
|
|||
|
</ul>
|
|||
|
</section>
|
|||
|
<section id="references">
|
|||
|
<h2>References<a class="headerlink" href="#references" title="Permalink to this heading">#</a></h2>
|
|||
|
<ul class="simple">
|
|||
|
<li><p>Sutton, R. S. (1996). Generalization in Reinforcement Learning: Successful Examples Using Sparse Coarse Coding.
|
|||
|
In D. Touretzky, M. C. Mozer, & M. Hasselmo (Eds.), Advances in Neural Information Processing Systems (Vol. 8).
|
|||
|
MIT Press. https://proceedings.neurips.cc/paper/1995/file/8f1d43620bc6bb580df6e80b0dc05c48-Paper.pdf</p></li>
|
|||
|
<li><p>Sutton, R. S., Barto, A. G. (2018 ). Reinforcement Learning: An Introduction. The MIT Press.</p></li>
|
|||
|
</ul>
|
|||
|
</section>
|
|||
|
</section>
|
|||
|
|
|||
|
</article>
|
|||
|
</div>
|
|||
|
<footer>
|
|||
|
|
|||
|
<div class="related-pages">
|
|||
|
<a class="next-page" href="../cart_pole/">
|
|||
|
<div class="page-info">
|
|||
|
<div class="context">
|
|||
|
<span>Next</span>
|
|||
|
</div>
|
|||
|
<div class="title">Cart Pole</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="#">Acrobot</a><ul>
|
|||
|
<li><a class="reference internal" href="#description">Description</a></li>
|
|||
|
<li><a class="reference internal" href="#action-space">Action Space</a></li>
|
|||
|
<li><a class="reference internal" href="#observation-space">Observation Space</a></li>
|
|||
|
<li><a class="reference internal" href="#rewards">Rewards</a></li>
|
|||
|
<li><a class="reference internal" href="#starting-state">Starting State</a></li>
|
|||
|
<li><a class="reference internal" href="#episode-end">Episode End</a></li>
|
|||
|
<li><a class="reference internal" href="#arguments">Arguments</a></li>
|
|||
|
<li><a class="reference internal" href="#version-history">Version History</a></li>
|
|||
|
<li><a class="reference internal" href="#references">References</a></li>
|
|||
|
</ul>
|
|||
|
</li>
|
|||
|
</ul>
|
|||
|
|
|||
|
</div>
|
|||
|
</div>
|
|||
|
</div>
|
|||
|
|
|||
|
|
|||
|
</aside>
|
|||
|
</div>
|
|||
|
</div>
|
|||
|
</div>
|
|||
|
<script>
|
|||
|
const toggleMenu = () => {
|
|||
|
const menuBtn = document.querySelector(".farama-header-menu__btn");
|
|||
|
const menuContainer = document.querySelector(".farama-header-menu-container");
|
|||
|
if (document.querySelector(".farama-header-menu").classList.contains("active")) {
|
|||
|
menuBtn.setAttribute("aria-expanded", "false");
|
|||
|
menuContainer.setAttribute("aria-hidden", "true");
|
|||
|
} else {
|
|||
|
menuBtn.setAttribute("aria-expanded", "true");
|
|||
|
menuContainer.setAttribute("aria-hidden", "false");
|
|||
|
}
|
|||
|
document.querySelector(".farama-header-menu").classList.toggle("active");
|
|||
|
}
|
|||
|
|
|||
|
document.querySelector(".farama-header-menu__btn").addEventListener("click", toggleMenu);
|
|||
|
document.getElementById("farama-close-menu").addEventListener("click", toggleMenu);
|
|||
|
</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/doctools.js"></script>
|
|||
|
<script src="../../../_static/sphinx_highlight.js"></script>
|
|||
|
<script src="../../../_static/scripts/furo.js"></script>
|
|||
|
|
|||
|
<script>
|
|||
|
const createCORSRequest = (method, url) => {
|
|||
|
let xhr = new XMLHttpRequest();
|
|||
|
xhr.responseType = 'json';
|
|||
|
|
|||
|
if ("withCredentials" in xhr) {
|
|||
|
xhr.open(method, url, true);
|
|||
|
} else if (typeof XDomainRequest != "undefined") {
|
|||
|
// IE8 & IE9
|
|||
|
xhr = new XDomainRequest();
|
|||
|
xhr.open(method, url);
|
|||
|
} else {
|
|||
|
// CORS not supported.
|
|||
|
xhr = null;
|
|||
|
}
|
|||
|
return xhr;
|
|||
|
};
|
|||
|
|
|||
|
const url = 'https://farama.org/api/projects.json';
|
|||
|
const imagesBasepath = "https://farama.org/assets/images"
|
|||
|
const method = 'GET';
|
|||
|
let xhr = createCORSRequest(method, url);
|
|||
|
|
|||
|
xhr.onload = () => {
|
|||
|
const jsonResponse = xhr.response;
|
|||
|
const sections = {
|
|||
|
"Documentation": [],
|
|||
|
"Mature Projects": [],
|
|||
|
"Incubating Projects": [],
|
|||
|
"Foundation": [
|
|||
|
{
|
|||
|
name: "About",
|
|||
|
link: "https://farama.org/about"
|
|||
|
},
|
|||
|
{
|
|||
|
name: "Standards",
|
|||
|
link: "https://farama.org/project_standards",
|
|||
|
},
|
|||
|
{
|
|||
|
name: "Donate",
|
|||
|
link: "https://farama.org/donations"
|
|||
|
}
|
|||
|
]
|
|||
|
}
|
|||
|
Object.keys(jsonResponse).forEach(key => {
|
|||
|
projectJson = jsonResponse[key];
|
|||
|
if (projectJson.website !== null) {
|
|||
|
projectJson.link = projectJson.website;
|
|||
|
sections["Documentation"].push(projectJson)
|
|||
|
} else if (projectJson.type == "mature") {
|
|||
|
projectJson.link = projectJson.github;
|
|||
|
sections["Mature Projects"].push(projectJson)
|
|||
|
} else {
|
|||
|
projectJson.link = projectJson.github;
|
|||
|
sections["Incubating Projects"].push(projectJson)
|
|||
|
}
|
|||
|
})
|
|||
|
|
|||
|
const menuContainer = document.querySelector(".farama-header-menu__body");
|
|||
|
|
|||
|
Object.keys(sections).forEach((key, i) => {
|
|||
|
projects = sections[key];
|
|||
|
const sectionElem = Object.assign(
|
|||
|
document.createElement('div'), {
|
|||
|
className:'farama-header-menu__section',
|
|||
|
style: "padding-left: 24px"
|
|||
|
}
|
|||
|
)
|
|||
|
sectionElem.appendChild(Object.assign(document.createElement('span'),
|
|||
|
{
|
|||
|
className:'farama-header-menu__section-title' ,
|
|||
|
innerText: key
|
|||
|
}
|
|||
|
))
|
|||
|
const ulElem = Object.assign(document.createElement('ul'),
|
|||
|
{
|
|||
|
className:'farama-header-menu-list',
|
|||
|
}
|
|||
|
)
|
|||
|
for (let project of projects) {
|
|||
|
const liElem = document.createElement("li");
|
|||
|
const aElem = Object.assign(document.createElement("a"),
|
|||
|
{
|
|||
|
href: project.link
|
|||
|
}
|
|||
|
);
|
|||
|
liElem.appendChild(aElem);
|
|||
|
if (key !== "Foundation") {
|
|||
|
const imgElem = Object.assign(document.createElement("img"),
|
|||
|
{
|
|||
|
src: project.image ? imagesBasepath + project.image : imagesBasepath + "/farama_black.svg",
|
|||
|
alt: `${project.name} logo`,
|
|||
|
className: "farama-black-logo-invert"
|
|||
|
}
|
|||
|
);
|
|||
|
aElem.appendChild(imgElem);
|
|||
|
}
|
|||
|
aElem.appendChild(document.createTextNode(project.name));
|
|||
|
ulElem.appendChild(liElem);
|
|||
|
}
|
|||
|
sectionElem.appendChild(ulElem);
|
|||
|
menuContainer.appendChild(sectionElem)
|
|||
|
});
|
|||
|
}
|
|||
|
|
|||
|
xhr.onerror = function() {
|
|||
|
console.error("Unable to load projects");
|
|||
|
};
|
|||
|
|
|||
|
xhr.send();
|
|||
|
</script>
|
|||
|
|
|||
|
|
|||
|
<script>
|
|||
|
const versioningConfig = {
|
|||
|
githubUser: 'Farama-Foundation',
|
|||
|
githubRepo: 'Gymnasium',
|
|||
|
};
|
|||
|
fetch('/main/_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>
|