mirror of
https://github.com/Farama-Foundation/Gymnasium.git
synced 2025-08-20 05:52:03 +00:00
628 lines
36 KiB
HTML
628 lines
36 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="generator" content="Docutils 0.18.1: http://docutils.sourceforge.net/" />
|
|||
|
<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"/><meta name="generator" content="sphinx-5.1.1, furo 2022.06.21"/>
|
|||
|
<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=40978830699223671f4072448e654b5958f38b89" />
|
|||
|
<link rel="stylesheet" type="text/css" href="../../../_static/styles/furo-extensions.css?digest=30d1aed668e5c3a91c3e3bf6a60b675221979f0e" />
|
|||
|
<link rel="stylesheet" type="text/css" href="../../../_static/css/custom.css" />
|
|||
|
|
|||
|
|
|||
|
|
|||
|
|
|||
|
<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>
|
|||
|
|
|||
|
<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="sidebar-brand" href="../../../">
|
|||
|
|
|||
|
<div class="sidebar-logo-container">
|
|||
|
<img class="sidebar-logo only-light" src="../../../_static/img/gymnasium_black.svg" alt="Light Logo"/>
|
|||
|
<img class="sidebar-logo only-dark" src="../../../_static/img/gymnasium_white.svg" alt="Dark Logo"/>
|
|||
|
</div>
|
|||
|
|
|||
|
<span class="sidebar-brand-text">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>
|
|||
|
</ul>
|
|||
|
<p class="caption" role="heading"><span class="caption-text">API</span></p>
|
|||
|
<ul>
|
|||
|
<li class="toctree-l1"><a class="reference internal" href="../../../api/core/">Core</a></li>
|
|||
|
<li class="toctree-l1"><a class="reference internal" href="../../../api/spaces/">Spaces</a></li>
|
|||
|
<li class="toctree-l1"><a class="reference internal" href="../../../api/spaces_utils/">Spaces Utils</a></li>
|
|||
|
<li class="toctree-l1"><a class="reference internal" href="../../../api/wrappers/">Wrappers</a></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 class="current">
|
|||
|
<li class="toctree-l1 has-children"><a class="reference internal" href="../../atari/">Atari</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="../../atari/adventure/">Adventure</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/air_raid/">Air Raid</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/bank_heist/">Bank Heist</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/battle_zone/">Battle Zone</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/beam_rider/">Beam Rider</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/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/centipede/">Centipede</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/chopper_command/">Chopper Command</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/crazy_climber/">Crazy Climber</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/">Demon Attack</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/double_dunk/">Double Dunk</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/elevator_action/">Elevator Action</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/fishing_derby/">FishingDerby</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/frostbite/">Frostbite</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/hero/">Hero</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/kangaroo/">Kangaroo</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/">Kung Fu Master</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/montezuma_revenge/">Montezuma Revenge</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/ms_pacman/">Ms Pacman</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/name_this_game/">Name This Game</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/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/">Road Runner</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/robotank/">Robot Tank</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/skiing/">Skiings</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/star_gunner/">StarGunner</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/time_pilot/">TimePilot</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/">Up n’ Down</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_pinball/">Video Pinball</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/wizard_of_wor/">Wizard of Wor</a></li>
|
|||
|
<li class="toctree-l2"><a class="reference internal" href="../../atari/zaxxon/">Zaxxon</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-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="../../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/walker2d/">Walker2D</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-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="../../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 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"><a class="reference internal" href="../../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="../../../content/environment_creation/">Make your own custom environment</a></li>
|
|||
|
<li class="toctree-l1"><a class="reference internal" href="../../../content/vectorising/">Vectorising your environments</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://farama.org/donations">Donate</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="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="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 <a href='..'>Classic Control environments</a>. Please read that page first for general information.</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>Discrete(3)</p></td>
|
|||
|
</tr>
|
|||
|
<tr class="row-odd"><td><p>Observation Shape</p></td>
|
|||
|
<td><p>(6,)</p></td>
|
|||
|
</tr>
|
|||
|
<tr class="row-even"><td><p>Observation High</p></td>
|
|||
|
<td><p>[ 1. 1. 1. 1. 12.57 28.27]</p></td>
|
|||
|
</tr>
|
|||
|
<tr class="row-odd"><td><p>Observation Low</p></td>
|
|||
|
<td><p>[ -1. -1. -1. -1. -12.57 -28.27]</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.</p>
|
|||
|
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">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="s1">'Acrobot-v1'</span><span class="p">)</span>
|
|||
|
</pre></div>
|
|||
|
</div>
|
|||
|
<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-default 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">env</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 and
|
|||
|
the <a class="reference external" href="https://github.com/Farama-Foundation/gymnasium/blob/master/gymnasium/envs/classic_control/acrobot.py">implementation</a> 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><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/scripts/furo.js"></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_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>
|
|||
|
|
|||
|
<!-- Google tag (gtag.js) -->
|
|||
|
<script async src="https://www.googletagmanager.com/gtag/js?id=G-JGXSLW7N06"></script>
|
|||
|
<script>
|
|||
|
window.dataLayer = window.dataLayer || [];
|
|||
|
function gtag(){dataLayer.push(arguments);}
|
|||
|
gtag('js', new Date());
|
|||
|
|
|||
|
gtag('config', 'G-JGXSLW7N06');
|
|||
|
</script></body>
|
|||
|
</html>
|