mirror of
https://github.com/Farama-Foundation/Gymnasium.git
synced 2025-08-20 22:12:03 +00:00
1122 lines
66 KiB
HTML
1122 lines
66 KiB
HTML
|
<!doctype html>
|
|||
|
|
<html class="no-js" lang="en" data-content_root="../../../">
|
|||
|
|
<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/mujoco/inverted_double_pendulum.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="viewport" content="width=device-width, initial-scale=1" />
|
|||
|
|
<link rel="index" title="Index" href="../../../genindex/" /><link rel="search" title="Search" href="../../../search/" /><link rel="next" title="Inverted Pendulum" href="../inverted_pendulum/" /><link rel="prev" title="Humanoid Standup" href="../humanoid_standup/" />
|
|||
|
|
<link rel="canonical" href="https://gymnasium.farama.org/environments/mujoco/inverted_double_pendulum.html" />
|
|||
|
|
|
|||
|
|
<link rel="shortcut icon" href="../../../_static/favicon.png"/><!-- Generated with Sphinx 7.2.6 and Furo 2023.08.19.dev1 -->
|
|||
|
|
<title>Inverted Double Pendulum - Gymnasium Documentation</title>
|
|||
|
|
<link rel="stylesheet" type="text/css" href="../../../_static/pygments.css?v=a746c00c" />
|
|||
|
|
<link rel="stylesheet" type="text/css" href="../../../_static/styles/furo.css?v=3e7f4c72" />
|
|||
|
|
<link rel="stylesheet" type="text/css" href="../../../_static/sg_gallery.css?v=61a4c737" />
|
|||
|
|
<link rel="stylesheet" type="text/css" href="../../../_static/sg_gallery-binder.css?v=f4aeca0c" />
|
|||
|
|
<link rel="stylesheet" type="text/css" href="../../../_static/sg_gallery-dataframe.css?v=2082cf3c" />
|
|||
|
|
<link rel="stylesheet" type="text/css" href="../../../_static/sg_gallery-rendered-html.css?v=1277b6f3" />
|
|||
|
|
<link rel="stylesheet" type="text/css" href="../../../_static/styles/furo-extensions.css?v=49cbaffd" />
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
<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>
|
|||
|
|
</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="../../../introduction/basic_usage/">Basic Usage</a></li>
|
|||
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../introduction/train_agent/">Training an Agent</a></li>
|
|||
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../introduction/create_custom_env/">Create a Custom Environment</a></li>
|
|||
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../introduction/record_agent/">Recording Agents</a></li>
|
|||
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../introduction/speed_up_env/">Speeding Up Training</a></li>
|
|||
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../introduction/gym_compatibility/">Compatibility with Gym</a></li>
|
|||
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../introduction/migration_guide/">Migration Guide - v0.21 to v1.0.0</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/">Make and register</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 navigation of Spaces</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/vector/utils/">Utility functions</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 navigation of Wrappers</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/table/">List of Wrappers</a></li>
|
|||
|
|
<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 has-children"><a class="reference internal" href="../../../api/vector/">Vectorize</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 navigation of Vectorize</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/vector/wrappers/">Wrappers</a></li>
|
|||
|
|
<li class="toctree-l2"><a class="reference internal" href="../../../api/vector/async_vector_env/">AsyncVectorEnv</a></li>
|
|||
|
|
<li class="toctree-l2"><a class="reference internal" href="../../../api/vector/sync_vector_env/">SyncVectorEnv</a></li>
|
|||
|
|
<li class="toctree-l2"><a class="reference internal" href="../../../api/vector/utils/">Utility functions</a></li>
|
|||
|
|
</ul>
|
|||
|
|
</li>
|
|||
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../api/utils/">Utility functions</a></li>
|
|||
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../api/functional/">Functional Env</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="../../classic_control/">Classic Control</a><input class="toctree-checkbox" id="toctree-checkbox-4" name="toctree-checkbox-4" role="switch" type="checkbox"/><label for="toctree-checkbox-4"><div class="visually-hidden">Toggle navigation of Classic Control</div><i class="icon"><svg><use href="#svg-arrow-right"></use></svg></i></label><ul>
|
|||
|
|
<li class="toctree-l2"><a class="reference internal" href="../../classic_control/acrobot/">Acrobot</a></li>
|
|||
|
|
<li class="toctree-l2"><a class="reference internal" href="../../classic_control/cart_pole/">Cart Pole</a></li>
|
|||
|
|
<li class="toctree-l2"><a class="reference internal" href="../../classic_control/mountain_car_continuous/">Mountain Car Continuous</a></li>
|
|||
|
|
<li class="toctree-l2"><a class="reference internal" href="../../classic_control/mountain_car/">Mountain Car</a></li>
|
|||
|
|
<li class="toctree-l2"><a class="reference internal" href="../../classic_control/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 navigation of Box2D</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 navigation of Toy Text</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="../">MuJoCo</a><input checked="" 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 navigation of MuJoCo</div><i class="icon"><svg><use href="#svg-arrow-right"></use></svg></i></label><ul class="current">
|
|||
|
|
<li class="toctree-l2"><a class="reference internal" href="../ant/">Ant</a></li>
|
|||
|
|
<li class="toctree-l2"><a class="reference internal" href="../half_cheetah/">Half Cheetah</a></li>
|
|||
|
|
<li class="toctree-l2"><a class="reference internal" href="../hopper/">Hopper</a></li>
|
|||
|
|
<li class="toctree-l2"><a class="reference internal" href="../humanoid/">Humanoid</a></li>
|
|||
|
|
<li class="toctree-l2"><a class="reference internal" href="../humanoid_standup/">Humanoid Standup</a></li>
|
|||
|
|
<li class="toctree-l2 current current-page"><a class="current reference internal" href="#">Inverted Double Pendulum</a></li>
|
|||
|
|
<li class="toctree-l2"><a class="reference internal" href="../inverted_pendulum/">Inverted Pendulum</a></li>
|
|||
|
|
<li class="toctree-l2"><a class="reference internal" href="../pusher/">Pusher</a></li>
|
|||
|
|
<li class="toctree-l2"><a class="reference internal" href="../reacher/">Reacher</a></li>
|
|||
|
|
<li class="toctree-l2"><a class="reference internal" href="../swimmer/">Swimmer</a></li>
|
|||
|
|
<li class="toctree-l2"><a class="reference internal" href="../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 navigation of Atari</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>
|
|||
|
|
</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 navigation of Gymnasium Basics</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 navigation of Training Agents</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 internal" href="../../../tutorials/third-party-tutorials/">Third-Party Tutorials</a></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 class="tex2jax_ignore mathjax_ignore" id="inverted-double-pendulum">
|
|||
|
|
<h1>Inverted Double Pendulum<a class="headerlink" href="#inverted-double-pendulum" title="Link to this heading">#</a></h1>
|
|||
|
|
<figure class="align-default" id="id1">
|
|||
|
|
<a class="reference internal image-reference" href="../../../_images/inverted_double_pendulum.gif"><img alt="../../../_images/inverted_double_pendulum.gif" src="../../../_images/inverted_double_pendulum.gif" style="width: 200px;" /></a>
|
|||
|
|
</figure>
|
|||
|
|
<p>This environment is part of the Mujoco 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">Box(-1.0,</span> <span class="pre">1.0,</span> <span class="pre">(1,),</span> <span class="pre">float32)</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(-inf,</span> <span class="pre">inf,</span> <span class="pre">(9,),</span> <span class="pre">float64)</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("InvertedDoublePendulum-v5")</span></code></p></td>
|
|||
|
|
</tr>
|
|||
|
|
</tbody>
|
|||
|
|
</table>
|
|||
|
|
</div>
|
|||
|
|
<section id="description">
|
|||
|
|
<h2>Description<a class="headerlink" href="#description" title="Link to this heading">#</a></h2>
|
|||
|
|
<p>This environment originates from control theory and builds on the cartpole environment based on the work of Barto, Sutton, and Anderson in <a class="reference external" href="https://ieeexplore.ieee.org/document/6313077">“Neuronlike adaptive elements that can solve difficult learning control problems”</a>,
|
|||
|
|
powered by the Mujoco physics simulator - allowing for more complex experiments (such as varying the effects of gravity or constraints).
|
|||
|
|
This environment involves a cart that can be moved linearly, with one pole attached to it and a second pole attached to the other end of the first pole (leaving the second pole as the only one with a free end).
|
|||
|
|
The cart can be pushed left or right, and the goal is to balance the second pole on top of the first pole, which is in turn on top of the cart, by applying continuous forces to the cart.</p>
|
|||
|
|
</section>
|
|||
|
|
<section id="action-space">
|
|||
|
|
<h2>Action Space<a class="headerlink" href="#action-space" title="Link to this heading">#</a></h2>
|
|||
|
|
<p>The agent take a 1-element vector for actions.
|
|||
|
|
The action space is a continuous <code class="docutils literal notranslate"><span class="pre">(action)</span></code> in <code class="docutils literal notranslate"><span class="pre">[-1,</span> <span class="pre">1]</span></code>, where <code class="docutils literal notranslate"><span class="pre">action</span></code> represents the
|
|||
|
|
numerical force applied to the cart (with magnitude representing the amount of force and
|
|||
|
|
sign representing the direction)</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>Control Min</p></th>
|
|||
|
|
<th class="head"><p>Control Max</p></th>
|
|||
|
|
<th class="head"><p>Name (in corresponding XML file)</p></th>
|
|||
|
|
<th class="head"><p>Joint</p></th>
|
|||
|
|
<th class="head"><p>Type (Unit)</p></th>
|
|||
|
|
</tr>
|
|||
|
|
</thead>
|
|||
|
|
<tbody>
|
|||
|
|
<tr class="row-even"><td><p>0</p></td>
|
|||
|
|
<td><p>Force applied on the cart</p></td>
|
|||
|
|
<td><p>-1</p></td>
|
|||
|
|
<td><p>1</p></td>
|
|||
|
|
<td><p>slider</p></td>
|
|||
|
|
<td><p>slide</p></td>
|
|||
|
|
<td><p>Force (N)</p></td>
|
|||
|
|
</tr>
|
|||
|
|
</tbody>
|
|||
|
|
</table>
|
|||
|
|
</div>
|
|||
|
|
</section>
|
|||
|
|
<section id="observation-space">
|
|||
|
|
<h2>Observation Space<a class="headerlink" href="#observation-space" title="Link to this heading">#</a></h2>
|
|||
|
|
<p>The observation space consists of the following parts (in order):</p>
|
|||
|
|
<ul class="simple">
|
|||
|
|
<li><p><em>qpos (1 element):</em> Position values of the robot’s cart.</p></li>
|
|||
|
|
<li><p><em>sin(qpos) (2 elements):</em> The sine of the angles of poles.</p></li>
|
|||
|
|
<li><p><em>cos(qpos) (2 elements):</em> The cosine of the angles of poles.</p></li>
|
|||
|
|
<li><p><em>qvel (3 elements):</em> The velocities of these individual body parts (their derivatives).</p></li>
|
|||
|
|
<li><p><em>qfrc_constraint (1 element):</em> Constraint force of the cart.
|
|||
|
|
There is one constraint force for contacts for each degree of freedom (3).
|
|||
|
|
The approach and handling of constraints by MuJoCo is unique to the simulator and is based on their research.
|
|||
|
|
More information can be found in their <a class="reference external" href="https://mujoco.readthedocs.io/en/latest/computation.html"><em>documentation</em></a> or in their paper <a class="reference external" href="https://homes.cs.washington.edu/~todorov/papers/TodorovICRA14.pdf">“Analytically-invertible dynamics with contacts and constraints: Theory and implementation in MuJoCo”</a>.</p></li>
|
|||
|
|
</ul>
|
|||
|
|
<p>The observation space is a <code class="docutils literal notranslate"><span class="pre">Box(-Inf,</span> <span class="pre">Inf,</span> <span class="pre">(9,),</span> <span class="pre">float64)</span></code> where the elements are as follows:</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>
|
|||
|
|
<th class="head"><p>Name (in corresponding XML file)</p></th>
|
|||
|
|
<th class="head"><p>Joint</p></th>
|
|||
|
|
<th class="head"><p>Type (Unit)</p></th>
|
|||
|
|
</tr>
|
|||
|
|
</thead>
|
|||
|
|
<tbody>
|
|||
|
|
<tr class="row-even"><td><p>0</p></td>
|
|||
|
|
<td><p>position of the cart along the linear surface</p></td>
|
|||
|
|
<td><p>-Inf</p></td>
|
|||
|
|
<td><p>Inf</p></td>
|
|||
|
|
<td><p>slider</p></td>
|
|||
|
|
<td><p>slide</p></td>
|
|||
|
|
<td><p>position (m)</p></td>
|
|||
|
|
</tr>
|
|||
|
|
<tr class="row-odd"><td><p>1</p></td>
|
|||
|
|
<td><p>sine of the angle between the cart and the first pole</p></td>
|
|||
|
|
<td><p>-Inf</p></td>
|
|||
|
|
<td><p>Inf</p></td>
|
|||
|
|
<td><p>sin(hinge)</p></td>
|
|||
|
|
<td><p>hinge</p></td>
|
|||
|
|
<td><p>unitless</p></td>
|
|||
|
|
</tr>
|
|||
|
|
<tr class="row-even"><td><p>2</p></td>
|
|||
|
|
<td><p>sine of the angle between the two poles</p></td>
|
|||
|
|
<td><p>-Inf</p></td>
|
|||
|
|
<td><p>Inf</p></td>
|
|||
|
|
<td><p>sin(hinge2)</p></td>
|
|||
|
|
<td><p>hinge</p></td>
|
|||
|
|
<td><p>unitless</p></td>
|
|||
|
|
</tr>
|
|||
|
|
<tr class="row-odd"><td><p>3</p></td>
|
|||
|
|
<td><p>cosine of the angle between the cart and the first pole</p></td>
|
|||
|
|
<td><p>-Inf</p></td>
|
|||
|
|
<td><p>Inf</p></td>
|
|||
|
|
<td><p>cos(hinge)</p></td>
|
|||
|
|
<td><p>hinge</p></td>
|
|||
|
|
<td><p>unitless</p></td>
|
|||
|
|
</tr>
|
|||
|
|
<tr class="row-even"><td><p>4</p></td>
|
|||
|
|
<td><p>cosine of the angle between the two poles</p></td>
|
|||
|
|
<td><p>-Inf</p></td>
|
|||
|
|
<td><p>Inf</p></td>
|
|||
|
|
<td><p>cos(hinge2)</p></td>
|
|||
|
|
<td><p>hinge</p></td>
|
|||
|
|
<td><p>unitless</p></td>
|
|||
|
|
</tr>
|
|||
|
|
<tr class="row-odd"><td><p>5</p></td>
|
|||
|
|
<td><p>velocity of the cart</p></td>
|
|||
|
|
<td><p>-Inf</p></td>
|
|||
|
|
<td><p>Inf</p></td>
|
|||
|
|
<td><p>slider</p></td>
|
|||
|
|
<td><p>slide</p></td>
|
|||
|
|
<td><p>velocity (m/s)</p></td>
|
|||
|
|
</tr>
|
|||
|
|
<tr class="row-even"><td><p>6</p></td>
|
|||
|
|
<td><p>angular velocity of the angle between the cart and the first pole</p></td>
|
|||
|
|
<td><p>-Inf</p></td>
|
|||
|
|
<td><p>Inf</p></td>
|
|||
|
|
<td><p>hinge</p></td>
|
|||
|
|
<td><p>hinge</p></td>
|
|||
|
|
<td><p>angular velocity (rad/s)</p></td>
|
|||
|
|
</tr>
|
|||
|
|
<tr class="row-odd"><td><p>7</p></td>
|
|||
|
|
<td><p>angular velocity of the angle between the two poles</p></td>
|
|||
|
|
<td><p>-Inf</p></td>
|
|||
|
|
<td><p>Inf</p></td>
|
|||
|
|
<td><p>hinge2</p></td>
|
|||
|
|
<td><p>hinge</p></td>
|
|||
|
|
<td><p>angular velocity (rad/s)</p></td>
|
|||
|
|
</tr>
|
|||
|
|
<tr class="row-even"><td><p>8</p></td>
|
|||
|
|
<td><p>constraint force - x</p></td>
|
|||
|
|
<td><p>-Inf</p></td>
|
|||
|
|
<td><p>Inf</p></td>
|
|||
|
|
<td><p>slider</p></td>
|
|||
|
|
<td><p>slide</p></td>
|
|||
|
|
<td><p>Force (N)</p></td>
|
|||
|
|
</tr>
|
|||
|
|
<tr class="row-odd"><td><p>excluded</p></td>
|
|||
|
|
<td><p>constraint force - y</p></td>
|
|||
|
|
<td><p>-Inf</p></td>
|
|||
|
|
<td><p>Inf</p></td>
|
|||
|
|
<td><p>slider</p></td>
|
|||
|
|
<td><p>slide</p></td>
|
|||
|
|
<td><p>Force (N)</p></td>
|
|||
|
|
</tr>
|
|||
|
|
<tr class="row-even"><td><p>excluded</p></td>
|
|||
|
|
<td><p>constraint force - z</p></td>
|
|||
|
|
<td><p>-Inf</p></td>
|
|||
|
|
<td><p>Inf</p></td>
|
|||
|
|
<td><p>slider</p></td>
|
|||
|
|
<td><p>slide</p></td>
|
|||
|
|
<td><p>Force (N)</p></td>
|
|||
|
|
</tr>
|
|||
|
|
</tbody>
|
|||
|
|
</table>
|
|||
|
|
</div>
|
|||
|
|
</section>
|
|||
|
|
<section id="rewards">
|
|||
|
|
<h2>Rewards<a class="headerlink" href="#rewards" title="Link to this heading">#</a></h2>
|
|||
|
|
<p>The total reward is: <em><strong>reward</strong></em> <em>=</em> <em>alive_bonus - distance_penalty - velocity_penalty</em>.</p>
|
|||
|
|
<ul class="simple">
|
|||
|
|
<li><p><em>alive_bonus</em>:
|
|||
|
|
Every timestep that the Inverted Pendulum is healthy (see definition in section “Episode End”),
|
|||
|
|
it gets a reward of fixed value <code class="docutils literal notranslate"><span class="pre">healthy_reward</span></code> (default is <span class="math notranslate nohighlight">\(10\)</span>).</p></li>
|
|||
|
|
<li><p><em>distance_penalty</em>:
|
|||
|
|
This reward is a measure of how far the <em>tip</em> of the second pendulum (the only free end) moves,
|
|||
|
|
and it is calculated as <span class="math notranslate nohighlight">\(0.01 x_{pole2-tip}^2 + (y_{pole2-tip}-2)^2\)</span>,
|
|||
|
|
where <span class="math notranslate nohighlight">\(x_{pole2-tip}, y_{pole2-tip}\)</span> are the xy-coordinatesof the tip of the second pole.</p></li>
|
|||
|
|
<li><p><em>velocity_penalty</em>:
|
|||
|
|
A negative reward to penalize the agent for moving too fast.
|
|||
|
|
<span class="math notranslate nohighlight">\(10^{-3} \omega_1 + 5 \times 10^{-3} \omega_2\)</span>,
|
|||
|
|
where <span class="math notranslate nohighlight">\(\omega_1, \omega_2\)</span> are the angular velocities of the hinges.</p></li>
|
|||
|
|
</ul>
|
|||
|
|
<p><code class="docutils literal notranslate"><span class="pre">info</span></code> contains the individual reward terms.</p>
|
|||
|
|
</section>
|
|||
|
|
<section id="starting-state">
|
|||
|
|
<h2>Starting State<a class="headerlink" href="#starting-state" title="Link to this heading">#</a></h2>
|
|||
|
|
<p>The initial position state is <span class="math notranslate nohighlight">\(\mathcal{U}_{[-reset\_noise\_scale \times I_{3}, reset\_noise\_scale \times I_{3}]}\)</span>.
|
|||
|
|
The initial velocity state is <span class="math notranslate nohighlight">\(\mathcal{N}(0_{3}, reset\_noise\_scale^2 \times I_{3})\)</span>.</p>
|
|||
|
|
<p>where <span class="math notranslate nohighlight">\(\mathcal{N}\)</span> is the multivariate normal distribution and <span class="math notranslate nohighlight">\(\mathcal{U}\)</span> is the multivariate uniform continuous distribution.</p>
|
|||
|
|
</section>
|
|||
|
|
<section id="episode-end">
|
|||
|
|
<h2>Episode End<a class="headerlink" href="#episode-end" title="Link to this heading">#</a></h2>
|
|||
|
|
<section id="termination">
|
|||
|
|
<h3>Termination<a class="headerlink" href="#termination" title="Link to this heading">#</a></h3>
|
|||
|
|
<p>The environment terminates when the Inverted Double Pendulum is unhealthy.
|
|||
|
|
The Inverted Double Pendulum is unhealthy if any of the following happens:</p>
|
|||
|
|
<p>1.Termination: The y_coordinate of the tip of the second pole <span class="math notranslate nohighlight">\(\leq 1\)</span>.</p>
|
|||
|
|
<p>Note: The maximum standing height of the system is 1.2 m when all the parts are perpendicularly vertical on top of each other.</p>
|
|||
|
|
</section>
|
|||
|
|
<section id="truncation">
|
|||
|
|
<h3>Truncation<a class="headerlink" href="#truncation" title="Link to this heading">#</a></h3>
|
|||
|
|
<p>The default duration of an episode is 1000 timesteps.</p>
|
|||
|
|
</section>
|
|||
|
|
</section>
|
|||
|
|
<section id="arguments">
|
|||
|
|
<h2>Arguments<a class="headerlink" href="#arguments" title="Link to this heading">#</a></h2>
|
|||
|
|
<p>InvertedDoublePendulum provides a range of parameters to modify the observation space, reward function, initial state, and termination condition.
|
|||
|
|
These parameters can be applied during <code class="docutils literal notranslate"><span class="pre">gymnasium.make</span></code> in the following way:</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">'InvertedDoublePendulum-v5'</span><span class="p">,</span> <span class="n">healthy_reward</span><span class="o">=</span><span class="mi">10</span><span class="p">,</span> <span class="o">...</span><span class="p">)</span>
|
|||
|
|
</pre></div>
|
|||
|
|
</div>
|
|||
|
|
<div class="table-wrapper colwidths-auto docutils container">
|
|||
|
|
<table class="docutils align-default">
|
|||
|
|
<thead>
|
|||
|
|
<tr class="row-odd"><th class="head"><p>Parameter</p></th>
|
|||
|
|
<th class="head"><p>Type</p></th>
|
|||
|
|
<th class="head"><p>Default</p></th>
|
|||
|
|
<th class="head"><p>Description</p></th>
|
|||
|
|
</tr>
|
|||
|
|
</thead>
|
|||
|
|
<tbody>
|
|||
|
|
<tr class="row-even"><td><p><code class="docutils literal notranslate"><span class="pre">xml_file</span></code></p></td>
|
|||
|
|
<td><p><strong>str</strong></p></td>
|
|||
|
|
<td><p><code class="docutils literal notranslate"><span class="pre">"inverted_double_pendulum.xml"</span></code></p></td>
|
|||
|
|
<td><p>Path to a MuJoCo model</p></td>
|
|||
|
|
</tr>
|
|||
|
|
<tr class="row-odd"><td><p><code class="docutils literal notranslate"><span class="pre">healthy_reward</span></code></p></td>
|
|||
|
|
<td><p><strong>float</strong></p></td>
|
|||
|
|
<td><p><code class="docutils literal notranslate"><span class="pre">10</span></code></p></td>
|
|||
|
|
<td><p>Constant reward given if the pendulum is <code class="docutils literal notranslate"><span class="pre">healthy</span></code> (upright) (see <code class="docutils literal notranslate"><span class="pre">Rewards</span></code> section)</p></td>
|
|||
|
|
</tr>
|
|||
|
|
<tr class="row-even"><td><p><code class="docutils literal notranslate"><span class="pre">reset_noise_scale</span></code></p></td>
|
|||
|
|
<td><p><strong>float</strong></p></td>
|
|||
|
|
<td><p><code class="docutils literal notranslate"><span class="pre">0.1</span></code></p></td>
|
|||
|
|
<td><p>Scale of random perturbations of initial position and velocity (see <code class="docutils literal notranslate"><span class="pre">Starting</span> <span class="pre">State</span></code> section)</p></td>
|
|||
|
|
</tr>
|
|||
|
|
</tbody>
|
|||
|
|
</table>
|
|||
|
|
</div>
|
|||
|
|
</section>
|
|||
|
|
<section id="version-history">
|
|||
|
|
<h2>Version History<a class="headerlink" href="#version-history" title="Link to this heading">#</a></h2>
|
|||
|
|
<ul class="simple">
|
|||
|
|
<li><p>v5:</p>
|
|||
|
|
<ul>
|
|||
|
|
<li><p>Minimum <code class="docutils literal notranslate"><span class="pre">mujoco</span></code> version is now 2.3.3.</p></li>
|
|||
|
|
<li><p>Added <code class="docutils literal notranslate"><span class="pre">default_camera_config</span></code> argument, a dictionary for setting the <code class="docutils literal notranslate"><span class="pre">mj_camera</span></code> properties, mainly useful for custom environments.</p></li>
|
|||
|
|
<li><p>Added <code class="docutils literal notranslate"><span class="pre">frame_skip</span></code> argument, used to configure the <code class="docutils literal notranslate"><span class="pre">dt</span></code> (duration of <code class="docutils literal notranslate"><span class="pre">step()</span></code>), default varies by environment check environment documentation pages.</p></li>
|
|||
|
|
<li><p>Fixed bug: <code class="docutils literal notranslate"><span class="pre">healthy_reward</span></code> was given on every step (even if the Pendulum is unhealthy), now it is only given if the DoublePendulum is healthy (not terminated)(related <a class="reference external" href="https://github.com/Farama-Foundation/Gymnasium/issues/500">GitHub issue</a>).</p></li>
|
|||
|
|
<li><p>Excluded the <code class="docutils literal notranslate"><span class="pre">qfrc_constraint</span></code> (“constraint force”) of the hinges from the observation space (as it was always 0, thus providing no useful information to the agent, resulting in slightly faster training) (related <a class="reference external" href="https://github.com/Farama-Foundation/Gymnasium/issues/228">GitHub issue</a>).</p></li>
|
|||
|
|
<li><p>Added <code class="docutils literal notranslate"><span class="pre">xml_file</span></code> argument.</p></li>
|
|||
|
|
<li><p>Added <code class="docutils literal notranslate"><span class="pre">reset_noise_scale</span></code> argument to set the range of initial states.</p></li>
|
|||
|
|
<li><p>Added <code class="docutils literal notranslate"><span class="pre">healthy_reward</span></code> argument to configure the reward function (defaults are effectively the same as in <code class="docutils literal notranslate"><span class="pre">v4</span></code>).</p></li>
|
|||
|
|
<li><p>Added individual reward terms in <code class="docutils literal notranslate"><span class="pre">info</span></code> ( <code class="docutils literal notranslate"><span class="pre">info["reward_survive"]</span></code>, <code class="docutils literal notranslate"><span class="pre">info["distance_penalty"]</span></code>, <code class="docutils literal notranslate"><span class="pre">info["velocity_penalty"]</span></code>).</p></li>
|
|||
|
|
</ul>
|
|||
|
|
</li>
|
|||
|
|
<li><p>v4: All MuJoCo environments now use the MuJoCo bindings in mujoco >= 2.1.3.</p></li>
|
|||
|
|
<li><p>v3: This environment does not have a v3 release.</p></li>
|
|||
|
|
<li><p>v2: All continuous control environments now use mujoco-py >= 1.50.</p></li>
|
|||
|
|
<li><p>v1: max_time_steps raised to 1000 for robot based tasks (including inverted pendulum).</p></li>
|
|||
|
|
<li><p>v0: Initial versions release.</p></li>
|
|||
|
|
</ul>
|
|||
|
|
</section>
|
|||
|
|
</section>
|
|||
|
|
|
|||
|
|
</article>
|
|||
|
|
</div>
|
|||
|
|
<footer>
|
|||
|
|
|
|||
|
|
<div class="related-pages">
|
|||
|
|
<a class="next-page" href="../inverted_pendulum/">
|
|||
|
|
<div class="page-info">
|
|||
|
|
<div class="context">
|
|||
|
|
<span>Next</span>
|
|||
|
|
</div>
|
|||
|
|
<div class="title">Inverted Pendulum</div>
|
|||
|
|
</div>
|
|||
|
|
<svg class="furo-related-icon">
|
|||
|
|
<use href="#svg-arrow-right"></use>
|
|||
|
|
</svg>
|
|||
|
|
</a>
|
|||
|
|
<a class="prev-page" href="../humanoid_standup/">
|
|||
|
|
<svg class="furo-related-icon">
|
|||
|
|
<use href="#svg-arrow-right"></use>
|
|||
|
|
</svg>
|
|||
|
|
<div class="page-info">
|
|||
|
|
<div class="context">
|
|||
|
|
<span>Previous</span>
|
|||
|
|
</div>
|
|||
|
|
|
|||
|
|
<div class="title">Humanoid Standup</div>
|
|||
|
|
|
|||
|
|
</div>
|
|||
|
|
</a>
|
|||
|
|
</div>
|
|||
|
|
<div class="bottom-of-page">
|
|||
|
|
<div class="left-details">
|
|||
|
|
<div class="copyright">
|
|||
|
|
Copyright © 2023 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">
|
|||
|
|
<a class="muted-link" href="https://github.com/Farama-Foundation/Gymnasium/"
|
|||
|
|
aria-label="On GitHub">
|
|||
|
|
<svg stroke="currentColor" fill="currentColor" stroke-width="0" viewBox="0 0 16 16">
|
|||
|
|
<path fill-rule="evenodd"
|
|||
|
|
d="M8 0C3.58 0 0 3.58 0 8c0 3.54 2.29 6.53 5.47 7.59.4.07.55-.17.55-.38 0-.19-.01-.82-.01-1.49-2.01.37-2.53-.49-2.69-.94-.09-.23-.48-.94-.82-1.13-.28-.15-.68-.52-.01-.53.63-.01 1.08.58 1.23.82.72 1.21 1.87.87 2.33.66.07-.52.28-.87.51-1.07-1.78-.2-3.64-.89-3.64-3.95 0-.87.31-1.59.82-2.15-.08-.2-.36-1.02.08-2.12 0 0 .67-.21 2.2.82.64-.18 1.32-.27 2-.27.68 0 1.36.09 2 .27 1.53-1.04 2.2-.82 2.2-.82.44 1.1.16 1.92.08 2.12.51.56.82 1.27.82 2.15 0 3.07-1.87 3.75-3.65 3.95.29.25.54.73.54 1.48 0 1.07-.01 1.93-.01 2.2 0 .21.15.46.55.38A8.013 8.013 0 0 0 16 8c0-4.42-3.58-8-8-8z">
|
|||
|
|
</path>
|
|||
|
|
</svg>
|
|||
|
|
</a>
|
|||
|
|
</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="#">Inverted Double Pendulum</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><ul>
|
|||
|
|
<li><a class="reference internal" href="#termination">Termination</a></li>
|
|||
|
|
<li><a class="reference internal" href="#truncation">Truncation</a></li>
|
|||
|
|
</ul>
|
|||
|
|
</li>
|
|||
|
|
<li><a class="reference internal" href="#arguments">Arguments</a></li>
|
|||
|
|
<li><a class="reference internal" href="#version-history">Version History</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 async src="https://www.googletagmanager.com/gtag/js?id=G-6H9C8TWXZ8"></script>
|
|||
|
|
<script>
|
|||
|
|
const enableGtag = () => {
|
|||
|
|
window.dataLayer = window.dataLayer || [];
|
|||
|
|
function gtag(){dataLayer.push(arguments);}
|
|||
|
|
gtag('js', new Date());
|
|||
|
|
gtag('config', 'G-6H9C8TWXZ8');
|
|||
|
|
}
|
|||
|
|
(() => {
|
|||
|
|
if (!localStorage.getItem("acceptedCookieAlert")) {
|
|||
|
|
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.`;
|
|||
|
|
containerElem.appendChild(textElem);
|
|||
|
|
|
|||
|
|
const declineBtn = Object.assign(document.createElement("button"),
|
|||
|
|
{
|
|||
|
|
innerText: "Deny",
|
|||
|
|
className: "farama-btn cookie-alert__button",
|
|||
|
|
id: "cookie-alert__decline",
|
|||
|
|
}
|
|||
|
|
);
|
|||
|
|
declineBtn.addEventListener("click", () => {
|
|||
|
|
localStorage.setItem("acceptedCookieAlert", false);
|
|||
|
|
boxElem.remove();
|
|||
|
|
});
|
|||
|
|
|
|||
|
|
const acceptBtn = Object.assign(document.createElement("button"),
|
|||
|
|
{
|
|||
|
|
innerText: "Allow",
|
|||
|
|
className: "farama-btn cookie-alert__button",
|
|||
|
|
id: "cookie-alert__accept",
|
|||
|
|
}
|
|||
|
|
);
|
|||
|
|
acceptBtn.addEventListener("click", () => {
|
|||
|
|
localStorage.setItem("acceptedCookieAlert", true);
|
|||
|
|
boxElem.remove();
|
|||
|
|
enableGtag();
|
|||
|
|
});
|
|||
|
|
|
|||
|
|
containerElem.appendChild(declineBtn);
|
|||
|
|
containerElem.appendChild(acceptBtn);
|
|||
|
|
boxElem.appendChild(containerElem);
|
|||
|
|
document.body.appendChild(boxElem);
|
|||
|
|
} else if (localStorage.getItem("acceptedCookieAlert") === "true") {
|
|||
|
|
enableGtag();
|
|||
|
|
}
|
|||
|
|
})()
|
|||
|
|
</script>
|
|||
|
|
|
|||
|
|
<script src="../../../_static/documentation_options.js?v=ed34540e"></script>
|
|||
|
|
<script src="../../../_static/doctools.js?v=888ff710"></script>
|
|||
|
|
<script src="../../../_static/sphinx_highlight.js?v=dc90522c"></script>
|
|||
|
|
<script src="../../../_static/scripts/furo.js?v=7660844c"></script>
|
|||
|
|
<script>window.MathJax = {"options": {"processHtmlClass": "tex2jax_process|mathjax_process|math|output_area"}}</script>
|
|||
|
|
<script defer="defer" src="https://cdn.jsdelivr.net/npm/mathjax@3/es5/tex-mml-chtml.js"></script>
|
|||
|
|
|
|||
|
|
<script>
|
|||
|
|
|
|||
|
|
const createProjectsList = (projects, displayImages) => {
|
|||
|
|
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 (displayImages) {
|
|||
|
|
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);
|
|||
|
|
}
|
|||
|
|
return ulElem;
|
|||
|
|
}
|
|||
|
|
|
|||
|
|
// Create menu with Farama projects by using the API at farama.org/api/projects.json
|
|||
|
|
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 = {
|
|||
|
|
"Core Projects": [],
|
|||
|
|
"Mature Projects": {
|
|||
|
|
"Documentation": [],
|
|||
|
|
"Repositories": [],
|
|||
|
|
},
|
|||
|
|
"Incubating Projects": {
|
|||
|
|
"Documentation": [],
|
|||
|
|
"Repositories": [],
|
|||
|
|
},
|
|||
|
|
"Foundation": [
|
|||
|
|
{
|
|||
|
|
name: "About",
|
|||
|
|
link: "https://farama.org/about"
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
name: "Standards",
|
|||
|
|
link: "https://farama.org/project_standards",
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
name: "Donate",
|
|||
|
|
link: "https://farama.org/donations"
|
|||
|
|
}
|
|||
|
|
]
|
|||
|
|
}
|
|||
|
|
|
|||
|
|
// Categorize projects
|
|||
|
|
Object.keys(jsonResponse).forEach(key => {
|
|||
|
|
projectJson = jsonResponse[key];
|
|||
|
|
if (projectJson.website !== null) {
|
|||
|
|
projectJson.link = projectJson.website;
|
|||
|
|
} else {
|
|||
|
|
projectJson.link = projectJson.github;
|
|||
|
|
}
|
|||
|
|
if (projectJson.type === "core") {
|
|||
|
|
sections["Core Projects"].push(projectJson)
|
|||
|
|
} else if (projectJson.type == "mature") {
|
|||
|
|
if (projectJson.website !== null) {
|
|||
|
|
sections["Mature Projects"]["Documentation"].push(projectJson)
|
|||
|
|
} else {
|
|||
|
|
sections["Mature Projects"]["Repositories"].push(projectJson)
|
|||
|
|
}
|
|||
|
|
} else {
|
|||
|
|
if (projectJson.website !== null) {
|
|||
|
|
sections["Incubating Projects"]["Documentation"].push(projectJson)
|
|||
|
|
} else {
|
|||
|
|
sections["Incubating Projects"]["Repositories"].push(projectJson)
|
|||
|
|
}
|
|||
|
|
}
|
|||
|
|
})
|
|||
|
|
|
|||
|
|
const menuContainer = document.querySelector(".farama-header-menu__body");
|
|||
|
|
|
|||
|
|
Object.keys(sections).forEach((key, i) => {
|
|||
|
|
const sectionElem = Object.assign(
|
|||
|
|
document.createElement('div'), {
|
|||
|
|
className:'farama-header-menu__section',
|
|||
|
|
}
|
|||
|
|
)
|
|||
|
|
sectionElem.appendChild(Object.assign(document.createElement('span'),
|
|||
|
|
{
|
|||
|
|
className:'farama-header-menu__section-title' ,
|
|||
|
|
innerText: key
|
|||
|
|
}
|
|||
|
|
))
|
|||
|
|
// is not a list
|
|||
|
|
if (sections[key].constructor !== Array) {
|
|||
|
|
const subSections = sections[key];
|
|||
|
|
const subSectionContainerElem = Object.assign(
|
|||
|
|
document.createElement('div'), {
|
|||
|
|
className:'farama-header-menu__subsections-container',
|
|||
|
|
style: 'display: flex'
|
|||
|
|
}
|
|||
|
|
)
|
|||
|
|
Object.keys(subSections).forEach((subKey, i) => {
|
|||
|
|
const subSectionElem = Object.assign(
|
|||
|
|
document.createElement('div'), {
|
|||
|
|
className:'farama-header-menu__subsection',
|
|||
|
|
}
|
|||
|
|
)
|
|||
|
|
subSectionElem.appendChild(Object.assign(document.createElement('span'),
|
|||
|
|
{
|
|||
|
|
className:'farama-header-menu__subsection-title' ,
|
|||
|
|
innerText: subKey
|
|||
|
|
}
|
|||
|
|
))
|
|||
|
|
const ulElem = createProjectsList(subSections[subKey], key !== 'Foundation');
|
|||
|
|
subSectionElem.appendChild(ulElem);
|
|||
|
|
subSectionContainerElem.appendChild(subSectionElem);
|
|||
|
|
})
|
|||
|
|
sectionElem.appendChild(subSectionContainerElem);
|
|||
|
|
} else {
|
|||
|
|
const projects = sections[key];
|
|||
|
|
const ulElem = createProjectsList(projects, true);
|
|||
|
|
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>
|