mirror of
https://github.com/Farama-Foundation/Gymnasium.git
synced 2025-08-19 21:42:02 +00:00
1173 lines
59 KiB
HTML
1173 lines
59 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/pusher.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="Reacher" href="../reacher/" /><link rel="prev" title="Inverted Pendulum" href="../inverted_pendulum/" />
|
||
<link rel="canonical" href="https://gymnasium.farama.org/environments/mujoco/pusher.html" />
|
||
|
||
<link rel="shortcut icon" href="../../../_static/favicon.png"/><!-- Generated with Sphinx 7.4.7 and Furo 2023.08.19.dev1 -->
|
||
<title>Pusher - Gymnasium Documentation</title>
|
||
<link rel="stylesheet" type="text/css" href="../../../_static/pygments.css?v=8f2a1f02" />
|
||
<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=82c8b628" />
|
||
|
||
|
||
|
||
|
||
<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>
|
||
</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"><a class="reference internal" href="../inverted_double_pendulum/">Inverted Double Pendulum</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../inverted_pendulum/">Inverted Pendulum</a></li>
|
||
<li class="toctree-l2 current current-page"><a class="current reference internal" href="#">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"><a class="reference internal" href="../../atari/">Atari</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../third_party_environments/">External 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 Documentation Links</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 Gymnasium Basics Documentation Links</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/load_quadruped_model/">Load custom quadruped robot environments</a></li>
|
||
<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 links in the Gymnasium Documentation</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 Training Agents links in the Gymnasium Documentation</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>
|
||
</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://arxiv.org/abs/2407.17032">Paper</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="pusher">
|
||
<h1>Pusher<a class="headerlink" href="#pusher" title="Link to this heading">¶</a></h1>
|
||
<figure class="align-default" id="id1">
|
||
<a class="reference internal image-reference" href="../../../_images/pusher.gif"><img alt="../../../_images/pusher.gif" src="../../../_images/pusher.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(-2.0,</span> <span class="pre">2.0,</span> <span class="pre">(7,),</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">(23,),</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("Pusher-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>“Pusher” is a multi-jointed robot arm that is very similar to a human arm.
|
||
The goal is to move a target cylinder (called <em>object</em>) to a goal position using the robot’s end effector (called <em>fingertip</em>).
|
||
The robot consists of shoulder, elbow, forearm and wrist joints.</p>
|
||
</section>
|
||
<section id="action-space">
|
||
<h2>Action Space<a class="headerlink" href="#action-space" title="Link to this heading">¶</a></h2>
|
||
<figure class="align-default" id="id2">
|
||
<img alt="../../../_images/pusher.png" src="../../../_images/pusher.png" />
|
||
</figure>
|
||
<p>The action space is a <code class="docutils literal notranslate"><span class="pre">Box(-2,</span> <span class="pre">2,</span> <span class="pre">(7,),</span> <span class="pre">float32)</span></code>. An action <code class="docutils literal notranslate"><span class="pre">(a,</span> <span class="pre">b)</span></code> represents the torques applied at the hinge joints.</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>Rotation of the panning the shoulder</p></td>
|
||
<td><p>-2</p></td>
|
||
<td><p>2</p></td>
|
||
<td><p>r_shoulder_pan_joint</p></td>
|
||
<td><p>hinge</p></td>
|
||
<td><p>torque (N m)</p></td>
|
||
</tr>
|
||
<tr class="row-odd"><td><p>1</p></td>
|
||
<td><p>Rotation of the shoulder lifting joint</p></td>
|
||
<td><p>-2</p></td>
|
||
<td><p>2</p></td>
|
||
<td><p>r_shoulder_lift_joint</p></td>
|
||
<td><p>hinge</p></td>
|
||
<td><p>torque (N m)</p></td>
|
||
</tr>
|
||
<tr class="row-even"><td><p>2</p></td>
|
||
<td><p>Rotation of the shoulder rolling joint</p></td>
|
||
<td><p>-2</p></td>
|
||
<td><p>2</p></td>
|
||
<td><p>r_upper_arm_roll_joint</p></td>
|
||
<td><p>hinge</p></td>
|
||
<td><p>torque (N m)</p></td>
|
||
</tr>
|
||
<tr class="row-odd"><td><p>3</p></td>
|
||
<td><p>Rotation of hinge joint that flexed the elbow</p></td>
|
||
<td><p>-2</p></td>
|
||
<td><p>2</p></td>
|
||
<td><p>r_elbow_flex_joint</p></td>
|
||
<td><p>hinge</p></td>
|
||
<td><p>torque (N m)</p></td>
|
||
</tr>
|
||
<tr class="row-even"><td><p>4</p></td>
|
||
<td><p>Rotation of hinge that rolls the forearm</p></td>
|
||
<td><p>-2</p></td>
|
||
<td><p>2</p></td>
|
||
<td><p>r_forearm_roll_joint</p></td>
|
||
<td><p>hinge</p></td>
|
||
<td><p>torque (N m)</p></td>
|
||
</tr>
|
||
<tr class="row-odd"><td><p>5</p></td>
|
||
<td><p>Rotation of flexing the wrist</p></td>
|
||
<td><p>-2</p></td>
|
||
<td><p>2</p></td>
|
||
<td><p>r_wrist_flex_joint</p></td>
|
||
<td><p>hinge</p></td>
|
||
<td><p>torque (N m)</p></td>
|
||
</tr>
|
||
<tr class="row-even"><td><p>6</p></td>
|
||
<td><p>Rotation of rolling the wrist</p></td>
|
||
<td><p>-2</p></td>
|
||
<td><p>2</p></td>
|
||
<td><p>r_wrist_roll_joint</p></td>
|
||
<td><p>hinge</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="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 (7 elements):</em> Position values of the robot’s body parts.</p></li>
|
||
<li><p><em>qvel (7 elements):</em> The velocities of these individual body parts (their derivatives).</p></li>
|
||
<li><p><em>xpos (3 elements):</em> The coordinates of the fingertip of the pusher.</p></li>
|
||
<li><p><em>xpos (3 elements):</em> The coordinates of the object to be moved.</p></li>
|
||
<li><p><em>xpos (3 elements):</em> The coordinates of the goal position.</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">(17,),</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>Rotation of the panning the shoulder</p></td>
|
||
<td><p>-Inf</p></td>
|
||
<td><p>Inf</p></td>
|
||
<td><p>r_shoulder_pan_joint</p></td>
|
||
<td><p>hinge</p></td>
|
||
<td><p>angle (rad)</p></td>
|
||
</tr>
|
||
<tr class="row-odd"><td><p>1</p></td>
|
||
<td><p>Rotation of the shoulder lifting joint</p></td>
|
||
<td><p>-Inf</p></td>
|
||
<td><p>Inf</p></td>
|
||
<td><p>r_shoulder_lift_joint</p></td>
|
||
<td><p>hinge</p></td>
|
||
<td><p>angle (rad)</p></td>
|
||
</tr>
|
||
<tr class="row-even"><td><p>2</p></td>
|
||
<td><p>Rotation of the shoulder rolling joint</p></td>
|
||
<td><p>-Inf</p></td>
|
||
<td><p>Inf</p></td>
|
||
<td><p>r_upper_arm_roll_joint</p></td>
|
||
<td><p>hinge</p></td>
|
||
<td><p>angle (rad)</p></td>
|
||
</tr>
|
||
<tr class="row-odd"><td><p>3</p></td>
|
||
<td><p>Rotation of hinge joint that flexed the elbow</p></td>
|
||
<td><p>-Inf</p></td>
|
||
<td><p>Inf</p></td>
|
||
<td><p>r_elbow_flex_joint</p></td>
|
||
<td><p>hinge</p></td>
|
||
<td><p>angle (rad)</p></td>
|
||
</tr>
|
||
<tr class="row-even"><td><p>4</p></td>
|
||
<td><p>Rotation of hinge that rolls the forearm</p></td>
|
||
<td><p>-Inf</p></td>
|
||
<td><p>Inf</p></td>
|
||
<td><p>r_forearm_roll_joint</p></td>
|
||
<td><p>hinge</p></td>
|
||
<td><p>angle (rad)</p></td>
|
||
</tr>
|
||
<tr class="row-odd"><td><p>5</p></td>
|
||
<td><p>Rotation of flexing the wrist</p></td>
|
||
<td><p>-Inf</p></td>
|
||
<td><p>Inf</p></td>
|
||
<td><p>r_wrist_flex_joint</p></td>
|
||
<td><p>hinge</p></td>
|
||
<td><p>angle (rad)</p></td>
|
||
</tr>
|
||
<tr class="row-even"><td><p>6</p></td>
|
||
<td><p>Rotation of rolling the wrist</p></td>
|
||
<td><p>-Inf</p></td>
|
||
<td><p>Inf</p></td>
|
||
<td><p>r_wrist_roll_joint</p></td>
|
||
<td><p>hinge</p></td>
|
||
<td><p>angle (rad)</p></td>
|
||
</tr>
|
||
<tr class="row-odd"><td><p>7</p></td>
|
||
<td><p>Rotational velocity of the panning the shoulder</p></td>
|
||
<td><p>-Inf</p></td>
|
||
<td><p>Inf</p></td>
|
||
<td><p>r_shoulder_pan_joint</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>Rotational velocity of the shoulder lifting joint</p></td>
|
||
<td><p>-Inf</p></td>
|
||
<td><p>Inf</p></td>
|
||
<td><p>r_shoulder_lift_joint</p></td>
|
||
<td><p>hinge</p></td>
|
||
<td><p>angular velocity (rad/s)</p></td>
|
||
</tr>
|
||
<tr class="row-odd"><td><p>9</p></td>
|
||
<td><p>Rotational velocity of the shoulder rolling joint</p></td>
|
||
<td><p>-Inf</p></td>
|
||
<td><p>Inf</p></td>
|
||
<td><p>r_upper_arm_roll_joint</p></td>
|
||
<td><p>hinge</p></td>
|
||
<td><p>angular velocity (rad/s)</p></td>
|
||
</tr>
|
||
<tr class="row-even"><td><p>10</p></td>
|
||
<td><p>Rotational velocity of hinge joint that flexed the elbow</p></td>
|
||
<td><p>-Inf</p></td>
|
||
<td><p>Inf</p></td>
|
||
<td><p>r_elbow_flex_joint</p></td>
|
||
<td><p>hinge</p></td>
|
||
<td><p>angular velocity (rad/s)</p></td>
|
||
</tr>
|
||
<tr class="row-odd"><td><p>11</p></td>
|
||
<td><p>Rotational velocity of hinge that rolls the forearm</p></td>
|
||
<td><p>-Inf</p></td>
|
||
<td><p>Inf</p></td>
|
||
<td><p>r_forearm_roll_joint</p></td>
|
||
<td><p>hinge</p></td>
|
||
<td><p>angular velocity (rad/s)</p></td>
|
||
</tr>
|
||
<tr class="row-even"><td><p>12</p></td>
|
||
<td><p>Rotational velocity of flexing the wrist</p></td>
|
||
<td><p>-Inf</p></td>
|
||
<td><p>Inf</p></td>
|
||
<td><p>r_wrist_flex_joint</p></td>
|
||
<td><p>hinge</p></td>
|
||
<td><p>angular velocity (rad/s)</p></td>
|
||
</tr>
|
||
<tr class="row-odd"><td><p>13</p></td>
|
||
<td><p>Rotational velocity of rolling the wrist</p></td>
|
||
<td><p>-Inf</p></td>
|
||
<td><p>Inf</p></td>
|
||
<td><p>r_wrist_roll_joint</p></td>
|
||
<td><p>hinge</p></td>
|
||
<td><p>angular velocity (rad/s)</p></td>
|
||
</tr>
|
||
<tr class="row-even"><td><p>14</p></td>
|
||
<td><p>x-coordinate of the fingertip of the pusher</p></td>
|
||
<td><p>-Inf</p></td>
|
||
<td><p>Inf</p></td>
|
||
<td><p>tips_arm</p></td>
|
||
<td><p>slide</p></td>
|
||
<td><p>position (m)</p></td>
|
||
</tr>
|
||
<tr class="row-odd"><td><p>15</p></td>
|
||
<td><p>y-coordinate of the fingertip of the pusher</p></td>
|
||
<td><p>-Inf</p></td>
|
||
<td><p>Inf</p></td>
|
||
<td><p>tips_arm</p></td>
|
||
<td><p>slide</p></td>
|
||
<td><p>position (m)</p></td>
|
||
</tr>
|
||
<tr class="row-even"><td><p>16</p></td>
|
||
<td><p>z-coordinate of the fingertip of the pusher</p></td>
|
||
<td><p>-Inf</p></td>
|
||
<td><p>Inf</p></td>
|
||
<td><p>tips_arm</p></td>
|
||
<td><p>slide</p></td>
|
||
<td><p>position (m)</p></td>
|
||
</tr>
|
||
<tr class="row-odd"><td><p>17</p></td>
|
||
<td><p>x-coordinate of the object to be moved</p></td>
|
||
<td><p>-Inf</p></td>
|
||
<td><p>Inf</p></td>
|
||
<td><p>object (obj_slidex)</p></td>
|
||
<td><p>slide</p></td>
|
||
<td><p>position (m)</p></td>
|
||
</tr>
|
||
<tr class="row-even"><td><p>18</p></td>
|
||
<td><p>y-coordinate of the object to be moved</p></td>
|
||
<td><p>-Inf</p></td>
|
||
<td><p>Inf</p></td>
|
||
<td><p>object (obj_slidey)</p></td>
|
||
<td><p>slide</p></td>
|
||
<td><p>position (m)</p></td>
|
||
</tr>
|
||
<tr class="row-odd"><td><p>19</p></td>
|
||
<td><p>z-coordinate of the object to be moved</p></td>
|
||
<td><p>-Inf</p></td>
|
||
<td><p>Inf</p></td>
|
||
<td><p>object</p></td>
|
||
<td><p>cylinder</p></td>
|
||
<td><p>position (m)</p></td>
|
||
</tr>
|
||
<tr class="row-even"><td><p>20</p></td>
|
||
<td><p>x-coordinate of the goal position of the object</p></td>
|
||
<td><p>-Inf</p></td>
|
||
<td><p>Inf</p></td>
|
||
<td><p>goal (goal_slidex)</p></td>
|
||
<td><p>slide</p></td>
|
||
<td><p>position (m)</p></td>
|
||
</tr>
|
||
<tr class="row-odd"><td><p>21</p></td>
|
||
<td><p>y-coordinate of the goal position of the object</p></td>
|
||
<td><p>-Inf</p></td>
|
||
<td><p>Inf</p></td>
|
||
<td><p>goal (goal_slidey)</p></td>
|
||
<td><p>slide</p></td>
|
||
<td><p>position (m)</p></td>
|
||
</tr>
|
||
<tr class="row-even"><td><p>22</p></td>
|
||
<td><p>z-coordinate of the goal position of the object</p></td>
|
||
<td><p>-Inf</p></td>
|
||
<td><p>Inf</p></td>
|
||
<td><p>goal</p></td>
|
||
<td><p>sphere</p></td>
|
||
<td><p>position (m)</p></td>
|
||
</tr>
|
||
</tbody>
|
||
</table>
|
||
</div>
|
||
<p>To understand the state space, an analogy can be drawn to a human arm, where the words “flex” and “roll” have the same meaning as in human joints.</p>
|
||
</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>reward_dist + reward_ctrl + reward_near</em>.</p>
|
||
<ul class="simple">
|
||
<li><p><em>reward_near</em>:
|
||
This reward is a measure of how far the <em>fingertip</em> of the pusher (the unattached end) is from the object,
|
||
with a more negative value assigned for when the pusher’s <em>fingertip</em> is further away from the target.
|
||
It is <span class="math notranslate nohighlight">\(-w_{near} \|(P_{fingertip} - P_{target})\|_2\)</span>.
|
||
where <span class="math notranslate nohighlight">\(w_{near}\)</span> is the <code class="docutils literal notranslate"><span class="pre">reward_near_weight</span></code> (default is <span class="math notranslate nohighlight">\(0.5\)</span>).</p></li>
|
||
<li><p><em>reward_dist</em>:
|
||
This reward is a measure of how far the object is from the target goal position,
|
||
with a more negative value assigned if the object is further away from the target.
|
||
It is <span class="math notranslate nohighlight">\(-w_{dist} \|(P_{object} - P_{target})\|_2\)</span>.
|
||
where <span class="math notranslate nohighlight">\(w_{dist}\)</span> is the <code class="docutils literal notranslate"><span class="pre">reward_dist_weight</span></code> (default is <span class="math notranslate nohighlight">\(1\)</span>).</p></li>
|
||
<li><p><em>reward_control</em>:
|
||
A negative reward to penalize the pusher for taking actions that are too large.
|
||
It is measured as the negative squared Euclidean norm of the action, i.e. as <span class="math notranslate nohighlight">\(-w_{control} \|action\|_2^2\)</span>.
|
||
where <span class="math notranslate nohighlight">\(w_{control}\)</span> is the <code class="docutils literal notranslate"><span class="pre">reward_control_weight</span></code> (default is <span class="math notranslate nohighlight">\(0.1\)</span>).</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 of the Pusher arm is <span class="math notranslate nohighlight">\(0_{6}\)</span>.
|
||
The initial position state of the object is <span class="math notranslate nohighlight">\(\mathcal{U}_{[[-0.3, -0.2], [0, 0.2]]}\)</span>.
|
||
The position state of the goal is (permanently) <span class="math notranslate nohighlight">\([0.45, -0.05, -0.323]\)</span>.
|
||
The initial velocity state of the Pusher arm is <span class="math notranslate nohighlight">\(\mathcal{U}_{[-0.005 \times I_{6}, 0.005 \times I_{6}]}\)</span>.
|
||
The initial velocity state of the object is <span class="math notranslate nohighlight">\(0_2\)</span>.
|
||
The velocity state of the goal is (permanently) <span class="math notranslate nohighlight">\(0_3\)</span>.</p>
|
||
<p>where <span class="math notranslate nohighlight">\(\mathcal{U}\)</span> is the multivariate uniform continuous distribution.</p>
|
||
<p>Note that the initial position state of the object is sampled until its distance to the goal is <span class="math notranslate nohighlight">\( > 0.17 m\)</span>.</p>
|
||
<p>The default frame rate is 5, with each frame lasting 0.01, so <em>dt = 5 * 0.01 = 0.05</em>.</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 Pusher never terminates.</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 100 timesteps.</p>
|
||
</section>
|
||
</section>
|
||
<section id="arguments">
|
||
<h2>Arguments<a class="headerlink" href="#arguments" title="Link to this heading">¶</a></h2>
|
||
<p>Pusher 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="w"> </span><span class="nn">gymnasium</span><span class="w"> </span><span class="k">as</span><span class="w"> </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">'Pusher-v5'</span><span class="p">,</span> <span class="n">xml_file</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">"pusher_v5.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">reward_near_weight</span></code></p></td>
|
||
<td><p><strong>float</strong></p></td>
|
||
<td><p><code class="docutils literal notranslate"><span class="pre">0.5</span></code></p></td>
|
||
<td><p>Weight for <em>reward_near</em> term (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">reward_dist_weight</span></code></p></td>
|
||
<td><p><strong>float</strong></p></td>
|
||
<td><p><code class="docutils literal notranslate"><span class="pre">1</span></code></p></td>
|
||
<td><p>Weight for <em>reward_dist</em> term (see <code class="docutils literal notranslate"><span class="pre">Rewards</span></code> section)</p></td>
|
||
</tr>
|
||
<tr class="row-odd"><td><p><code class="docutils literal notranslate"><span class="pre">reward_control_weight</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>Weight for <em>reward_control</em> term (see <code class="docutils literal notranslate"><span class="pre">Rewards</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>Fixed bug: increased the density of the object to be higher than air (related <a class="reference external" href="https://github.com/Farama-Foundation/Gymnasium/issues/950">GitHub issue</a>).</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>Added <code class="docutils literal notranslate"><span class="pre">xml_file</span></code> argument.</p></li>
|
||
<li><p>Fixed bug: <code class="docutils literal notranslate"><span class="pre">reward_distance</span></code> & <code class="docutils literal notranslate"><span class="pre">reward_near</span></code> was based on the state before the physics step, now it is based on the state after the physics step (related <a class="reference external" href="https://github.com/Farama-Foundation/Gymnasium/issues/821">GitHub issue</a>).</p></li>
|
||
<li><p>Added <code class="docutils literal notranslate"><span class="pre">reward_near_weight</span></code>, <code class="docutils literal notranslate"><span class="pre">reward_dist_weight</span></code>, <code class="docutils literal notranslate"><span class="pre">reward_control_weight</span></code> arguments 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>Fixed <code class="docutils literal notranslate"><span class="pre">info["reward_ctrl"]</span></code> not being multiplied by the reward weight.</p></li>
|
||
<li><p>Added <code class="docutils literal notranslate"><span class="pre">info["reward_near"]</span></code> which is equal to the reward term <code class="docutils literal notranslate"><span class="pre">reward_near</span></code>.</p></li>
|
||
</ul>
|
||
</li>
|
||
<li><p>v4: All MuJoCo environments now use the MuJoCo bindings in mujoco >= 2.1.3.</p>
|
||
<ul>
|
||
<li><p>Warning: This version of the environment is not compatible with <code class="docutils literal notranslate"><span class="pre">mujoco>=3.0.0</span></code> (related <a class="reference external" href="https://github.com/Farama-Foundation/Gymnasium/issues/950">GitHub issue</a>).</p></li>
|
||
</ul>
|
||
</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 (not including pusher, which has a max_time_steps of 100). Added reward_threshold to environments.</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="../reacher/">
|
||
<div class="page-info">
|
||
<div class="context">
|
||
<span>Next</span>
|
||
</div>
|
||
<div class="title">Reacher</div>
|
||
</div>
|
||
<svg class="furo-related-icon">
|
||
<use href="#svg-arrow-right"></use>
|
||
</svg>
|
||
</a>
|
||
<a class="prev-page" href="../inverted_pendulum/">
|
||
<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">Inverted Pendulum</div>
|
||
|
||
</div>
|
||
</a>
|
||
</div>
|
||
<div class="bottom-of-page">
|
||
<div class="left-details">
|
||
<div class="copyright">
|
||
Copyright © 2025 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="#">Pusher</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=25d39d6f"></script>
|
||
<script src="../../../_static/doctools.js?v=9a2dae69"></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> |