mirror of
https://github.com/Farama-Foundation/Gymnasium.git
synced 2025-08-17 20:39:12 +00:00
1384 lines
120 KiB
HTML
1384 lines
120 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/_modules/gymnasium/core.html" /><meta property="og:image" content="https://gymnasium.farama.org/_static/img/gymnasium-github.png" /><meta name="twitter:card" content="summary_large_image"><link rel="index" title="Index" href="../../../genindex/" /><link rel="search" title="Search" href="../../../search/" />
|
||
<link rel="canonical" href="https://gymnasium.farama.org/_modules/gymnasium/core.html" />
|
||
|
||
<link rel="shortcut icon" href="../../../_static/favicon.png"/><!-- Generated with Sphinx 7.4.7 and Furo 2023.08.19.dev1 -->
|
||
<title>gymnasium.core - 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 no-toc" 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>
|
||
<li class="toctree-l1 has-children"><a class="reference internal" href="../../../environments/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="../../../environments/classic_control/acrobot/">Acrobot</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../environments/classic_control/cart_pole/">Cart Pole</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../environments/classic_control/mountain_car_continuous/">Mountain Car Continuous</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../environments/classic_control/mountain_car/">Mountain Car</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../environments/classic_control/pendulum/">Pendulum</a></li>
|
||
</ul>
|
||
</li>
|
||
<li class="toctree-l1 has-children"><a class="reference internal" href="../../../environments/box2d/">Box2D</a><input class="toctree-checkbox" id="toctree-checkbox-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="../../../environments/box2d/bipedal_walker/">Bipedal Walker</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../environments/box2d/car_racing/">Car Racing</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../environments/box2d/lunar_lander/">Lunar Lander</a></li>
|
||
</ul>
|
||
</li>
|
||
<li class="toctree-l1 has-children"><a class="reference internal" href="../../../environments/toy_text/">Toy Text</a><input class="toctree-checkbox" id="toctree-checkbox-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="../../../environments/toy_text/blackjack/">Blackjack</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../environments/toy_text/taxi/">Taxi</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../environments/toy_text/cliff_walking/">Cliff Walking</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../environments/toy_text/frozen_lake/">Frozen Lake</a></li>
|
||
</ul>
|
||
</li>
|
||
<li class="toctree-l1 has-children"><a class="reference internal" href="../../../environments/mujoco/">MuJoCo</a><input class="toctree-checkbox" id="toctree-checkbox-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>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../environments/mujoco/ant/">Ant</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../environments/mujoco/half_cheetah/">Half Cheetah</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../environments/mujoco/hopper/">Hopper</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../environments/mujoco/humanoid/">Humanoid</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../environments/mujoco/humanoid_standup/">Humanoid Standup</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../environments/mujoco/inverted_double_pendulum/">Inverted Double Pendulum</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../environments/mujoco/inverted_pendulum/">Inverted Pendulum</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../environments/mujoco/pusher/">Pusher</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../environments/mujoco/reacher/">Reacher</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../environments/mujoco/swimmer/">Swimmer</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../environments/mujoco/walker2d/">Walker2D</a></li>
|
||
</ul>
|
||
</li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../environments/atari/">Atari</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../environments/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</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</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/environment_creation/">Make your own custom environment</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/load_quadruped_model/">Load custom quadruped robot environments</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-9" name="toctree-checkbox-9" role="switch" type="checkbox"/><label for="toctree-checkbox-9"><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/blackjack_q_learning/">Solving Blackjack with Tabular Q-Learning</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../tutorials/training_agents/frozenlake_q_learning/">Solving Frozenlake with Tabular Q-Learning</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../tutorials/training_agents/mujoco_reinforce/">Training using REINFORCE for Mujoco</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../tutorials/training_agents/vector_a2c/">Speeding up A2C Training with Vector Envs</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 no-toc" 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">
|
||
|
||
<h1>Source code for gymnasium.core</h1><div class="highlight"><pre>
|
||
<span></span><span class="sd">"""Core API for Environment, Wrapper, ActionWrapper, RewardWrapper and ObservationWrapper."""</span>
|
||
|
||
<span class="kn">from</span><span class="w"> </span><span class="nn">__future__</span><span class="w"> </span><span class="kn">import</span> <span class="n">annotations</span>
|
||
|
||
<span class="kn">from</span><span class="w"> </span><span class="nn">copy</span><span class="w"> </span><span class="kn">import</span> <span class="n">deepcopy</span>
|
||
<span class="kn">from</span><span class="w"> </span><span class="nn">typing</span><span class="w"> </span><span class="kn">import</span> <span class="n">TYPE_CHECKING</span><span class="p">,</span> <span class="n">Any</span><span class="p">,</span> <span class="n">Generic</span><span class="p">,</span> <span class="n">SupportsFloat</span><span class="p">,</span> <span class="n">TypeVar</span>
|
||
|
||
<span class="kn">import</span><span class="w"> </span><span class="nn">numpy</span><span class="w"> </span><span class="k">as</span><span class="w"> </span><span class="nn">np</span>
|
||
|
||
<span class="kn">import</span><span class="w"> </span><span class="nn">gymnasium</span>
|
||
<span class="kn">from</span><span class="w"> </span><span class="nn">gymnasium</span><span class="w"> </span><span class="kn">import</span> <span class="n">spaces</span>
|
||
<span class="kn">from</span><span class="w"> </span><span class="nn">gymnasium.utils</span><span class="w"> </span><span class="kn">import</span> <span class="n">RecordConstructorArgs</span><span class="p">,</span> <span class="n">seeding</span>
|
||
|
||
|
||
<span class="k">if</span> <span class="n">TYPE_CHECKING</span><span class="p">:</span>
|
||
<span class="kn">from</span><span class="w"> </span><span class="nn">gymnasium.envs.registration</span><span class="w"> </span><span class="kn">import</span> <span class="n">EnvSpec</span><span class="p">,</span> <span class="n">WrapperSpec</span>
|
||
|
||
<span class="n">ObsType</span> <span class="o">=</span> <span class="n">TypeVar</span><span class="p">(</span><span class="s2">"ObsType"</span><span class="p">)</span>
|
||
<span class="n">ActType</span> <span class="o">=</span> <span class="n">TypeVar</span><span class="p">(</span><span class="s2">"ActType"</span><span class="p">)</span>
|
||
<span class="n">RenderFrame</span> <span class="o">=</span> <span class="n">TypeVar</span><span class="p">(</span><span class="s2">"RenderFrame"</span><span class="p">)</span>
|
||
|
||
|
||
<div class="viewcode-block" id="Env">
|
||
<a class="viewcode-back" href="../../../api/env/#gymnasium.Env">[docs]</a>
|
||
<span class="k">class</span><span class="w"> </span><span class="nc">Env</span><span class="p">(</span><span class="n">Generic</span><span class="p">[</span><span class="n">ObsType</span><span class="p">,</span> <span class="n">ActType</span><span class="p">]):</span>
|
||
<span class="w"> </span><span class="sa">r</span><span class="sd">"""The main Gymnasium class for implementing Reinforcement Learning Agents environments.</span>
|
||
|
||
<span class="sd"> The class encapsulates an environment with arbitrary behind-the-scenes dynamics through the :meth:`step` and :meth:`reset` functions.</span>
|
||
<span class="sd"> An environment can be partially or fully observed by single agents. For multi-agent environments, see PettingZoo.</span>
|
||
|
||
<span class="sd"> The main API methods that users of this class need to know are:</span>
|
||
|
||
<span class="sd"> - :meth:`step` - Updates an environment with actions returning the next agent observation, the reward for taking that actions,</span>
|
||
<span class="sd"> if the environment has terminated or truncated due to the latest action and information from the environment about the step, i.e. metrics, debug info.</span>
|
||
<span class="sd"> - :meth:`reset` - Resets the environment to an initial state, required before calling step.</span>
|
||
<span class="sd"> Returns the first agent observation for an episode and information, i.e. metrics, debug info.</span>
|
||
<span class="sd"> - :meth:`render` - Renders the environments to help visualise what the agent see, examples modes are "human", "rgb_array", "ansi" for text.</span>
|
||
<span class="sd"> - :meth:`close` - Closes the environment, important when external software is used, i.e. pygame for rendering, databases</span>
|
||
|
||
<span class="sd"> Environments have additional attributes for users to understand the implementation</span>
|
||
|
||
<span class="sd"> - :attr:`action_space` - The Space object corresponding to valid actions, all valid actions should be contained within the space.</span>
|
||
<span class="sd"> - :attr:`observation_space` - The Space object corresponding to valid observations, all valid observations should be contained within the space.</span>
|
||
<span class="sd"> - :attr:`spec` - An environment spec that contains the information used to initialize the environment from :meth:`gymnasium.make`</span>
|
||
<span class="sd"> - :attr:`metadata` - The metadata of the environment, e.g. `{"render_modes": ["rgb_array", "human"], "render_fps": 30}`. For Jax or Torch, this can be indicated to users with `"jax"=True` or `"torch"=True`.</span>
|
||
<span class="sd"> - :attr:`np_random` - The random number generator for the environment. This is automatically assigned during</span>
|
||
<span class="sd"> ``super().reset(seed=seed)`` and when assessing :attr:`np_random`.</span>
|
||
|
||
<span class="sd"> .. seealso:: For modifying or extending environments use the :class:`gymnasium.Wrapper` class</span>
|
||
|
||
<span class="sd"> Note:</span>
|
||
<span class="sd"> To get reproducible sampling of actions, a seed can be set with ``env.action_space.seed(123)``.</span>
|
||
|
||
<span class="sd"> Note:</span>
|
||
<span class="sd"> For strict type checking (e.g. mypy or pyright), :class:`Env` is a generic class with two parameterized types: ``ObsType`` and ``ActType``.</span>
|
||
<span class="sd"> The ``ObsType`` and ``ActType`` are the expected types of the observations and actions used in :meth:`reset` and :meth:`step`.</span>
|
||
<span class="sd"> The environment's :attr:`observation_space` and :attr:`action_space` should have type ``Space[ObsType]`` and ``Space[ActType]``,</span>
|
||
<span class="sd"> see a space's implementation to find its parameterized type.</span>
|
||
<span class="sd"> """</span>
|
||
|
||
<span class="c1"># Set this in SOME subclasses</span>
|
||
<span class="n">metadata</span><span class="p">:</span> <span class="nb">dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">Any</span><span class="p">]</span> <span class="o">=</span> <span class="p">{</span><span class="s2">"render_modes"</span><span class="p">:</span> <span class="p">[]}</span>
|
||
<span class="c1"># define render_mode if your environment supports rendering</span>
|
||
<span class="n">render_mode</span><span class="p">:</span> <span class="nb">str</span> <span class="o">|</span> <span class="kc">None</span> <span class="o">=</span> <span class="kc">None</span>
|
||
<span class="n">spec</span><span class="p">:</span> <span class="n">EnvSpec</span> <span class="o">|</span> <span class="kc">None</span> <span class="o">=</span> <span class="kc">None</span>
|
||
|
||
<span class="c1"># Set these in ALL subclasses</span>
|
||
<span class="n">action_space</span><span class="p">:</span> <span class="n">spaces</span><span class="o">.</span><span class="n">Space</span><span class="p">[</span><span class="n">ActType</span><span class="p">]</span>
|
||
<span class="n">observation_space</span><span class="p">:</span> <span class="n">spaces</span><span class="o">.</span><span class="n">Space</span><span class="p">[</span><span class="n">ObsType</span><span class="p">]</span>
|
||
|
||
<span class="c1"># Created</span>
|
||
<span class="n">_np_random</span><span class="p">:</span> <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">Generator</span> <span class="o">|</span> <span class="kc">None</span> <span class="o">=</span> <span class="kc">None</span>
|
||
<span class="c1"># will be set to the "invalid" value -1 if the seed of the currently set rng is unknown</span>
|
||
<span class="n">_np_random_seed</span><span class="p">:</span> <span class="nb">int</span> <span class="o">|</span> <span class="kc">None</span> <span class="o">=</span> <span class="kc">None</span>
|
||
|
||
<div class="viewcode-block" id="Env.step">
|
||
<a class="viewcode-back" href="../../../api/env/#gymnasium.Env.step">[docs]</a>
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">step</span><span class="p">(</span>
|
||
<span class="bp">self</span><span class="p">,</span> <span class="n">action</span><span class="p">:</span> <span class="n">ActType</span>
|
||
<span class="p">)</span> <span class="o">-></span> <span class="nb">tuple</span><span class="p">[</span><span class="n">ObsType</span><span class="p">,</span> <span class="n">SupportsFloat</span><span class="p">,</span> <span class="nb">bool</span><span class="p">,</span> <span class="nb">bool</span><span class="p">,</span> <span class="nb">dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">Any</span><span class="p">]]:</span>
|
||
<span class="w"> </span><span class="sd">"""Run one timestep of the environment's dynamics using the agent actions.</span>
|
||
|
||
<span class="sd"> When the end of an episode is reached (``terminated or truncated``), it is necessary to call :meth:`reset` to</span>
|
||
<span class="sd"> reset this environment's state for the next episode.</span>
|
||
|
||
<span class="sd"> .. versionchanged:: 0.26</span>
|
||
|
||
<span class="sd"> The Step API was changed removing ``done`` in favor of ``terminated`` and ``truncated`` to make it clearer</span>
|
||
<span class="sd"> to users when the environment had terminated or truncated which is critical for reinforcement learning</span>
|
||
<span class="sd"> bootstrapping algorithms.</span>
|
||
|
||
<span class="sd"> Args:</span>
|
||
<span class="sd"> action (ActType): an action provided by the agent to update the environment state.</span>
|
||
|
||
<span class="sd"> Returns:</span>
|
||
<span class="sd"> observation (ObsType): An element of the environment's :attr:`observation_space` as the next observation due to the agent actions.</span>
|
||
<span class="sd"> An example is a numpy array containing the positions and velocities of the pole in CartPole.</span>
|
||
<span class="sd"> reward (SupportsFloat): The reward as a result of taking the action.</span>
|
||
<span class="sd"> terminated (bool): Whether the agent reaches the terminal state (as defined under the MDP of the task)</span>
|
||
<span class="sd"> which can be positive or negative. An example is reaching the goal state or moving into the lava from</span>
|
||
<span class="sd"> the Sutton and Barto Gridworld. If true, the user needs to call :meth:`reset`.</span>
|
||
<span class="sd"> truncated (bool): Whether the truncation condition outside the scope of the MDP is satisfied.</span>
|
||
<span class="sd"> Typically, this is a timelimit, but could also be used to indicate an agent physically going out of bounds.</span>
|
||
<span class="sd"> Can be used to end the episode prematurely before a terminal state is reached.</span>
|
||
<span class="sd"> If true, the user needs to call :meth:`reset`.</span>
|
||
<span class="sd"> info (dict): Contains auxiliary diagnostic information (helpful for debugging, learning, and logging).</span>
|
||
<span class="sd"> This might, for instance, contain: metrics that describe the agent's performance state, variables that are</span>
|
||
<span class="sd"> hidden from observations, or individual reward terms that are combined to produce the total reward.</span>
|
||
<span class="sd"> In OpenAI Gym <v26, it contains "TimeLimit.truncated" to distinguish truncation and termination,</span>
|
||
<span class="sd"> however this is deprecated in favour of returning terminated and truncated variables.</span>
|
||
<span class="sd"> done (bool): (Deprecated) A boolean value for if the episode has ended, in which case further :meth:`step` calls will</span>
|
||
<span class="sd"> return undefined results. This was removed in OpenAI Gym v26 in favor of terminated and truncated attributes.</span>
|
||
<span class="sd"> A done signal may be emitted for different reasons: Maybe the task underlying the environment was solved successfully,</span>
|
||
<span class="sd"> a certain timelimit was exceeded, or the physics simulation has entered an invalid state.</span>
|
||
<span class="sd"> """</span>
|
||
<span class="k">raise</span> <span class="ne">NotImplementedError</span></div>
|
||
|
||
|
||
<div class="viewcode-block" id="Env.reset">
|
||
<a class="viewcode-back" href="../../../api/env/#gymnasium.Env.reset">[docs]</a>
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">reset</span><span class="p">(</span>
|
||
<span class="bp">self</span><span class="p">,</span>
|
||
<span class="o">*</span><span class="p">,</span>
|
||
<span class="n">seed</span><span class="p">:</span> <span class="nb">int</span> <span class="o">|</span> <span class="kc">None</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span>
|
||
<span class="n">options</span><span class="p">:</span> <span class="nb">dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">Any</span><span class="p">]</span> <span class="o">|</span> <span class="kc">None</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span>
|
||
<span class="p">)</span> <span class="o">-></span> <span class="nb">tuple</span><span class="p">[</span><span class="n">ObsType</span><span class="p">,</span> <span class="nb">dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">Any</span><span class="p">]]:</span> <span class="c1"># type: ignore</span>
|
||
<span class="w"> </span><span class="sd">"""Resets the environment to an initial internal state, returning an initial observation and info.</span>
|
||
|
||
<span class="sd"> This method generates a new starting state often with some randomness to ensure that the agent explores the</span>
|
||
<span class="sd"> state space and learns a generalised policy about the environment. This randomness can be controlled</span>
|
||
<span class="sd"> with the ``seed`` parameter otherwise if the environment already has a random number generator and</span>
|
||
<span class="sd"> :meth:`reset` is called with ``seed=None``, the RNG is not reset.</span>
|
||
|
||
<span class="sd"> Therefore, :meth:`reset` should (in the typical use case) be called with a seed right after initialization and then never again.</span>
|
||
|
||
<span class="sd"> For Custom environments, the first line of :meth:`reset` should be ``super().reset(seed=seed)`` which implements</span>
|
||
<span class="sd"> the seeding correctly.</span>
|
||
|
||
<span class="sd"> .. versionchanged:: v0.25</span>
|
||
|
||
<span class="sd"> The ``return_info`` parameter was removed and now info is expected to be returned.</span>
|
||
|
||
<span class="sd"> Args:</span>
|
||
<span class="sd"> seed (optional int): The seed that is used to initialize the environment's PRNG (`np_random`) and</span>
|
||
<span class="sd"> the read-only attribute `np_random_seed`.</span>
|
||
<span class="sd"> If the environment does not already have a PRNG and ``seed=None`` (the default option) is passed,</span>
|
||
<span class="sd"> a seed will be chosen from some source of entropy (e.g. timestamp or /dev/urandom).</span>
|
||
<span class="sd"> However, if the environment already has a PRNG and ``seed=None`` is passed, the PRNG will *not* be reset</span>
|
||
<span class="sd"> and the env's :attr:`np_random_seed` will *not* be altered.</span>
|
||
<span class="sd"> If you pass an integer, the PRNG will be reset even if it already exists.</span>
|
||
<span class="sd"> Usually, you want to pass an integer *right after the environment has been initialized and then never again*.</span>
|
||
<span class="sd"> Please refer to the minimal example above to see this paradigm in action.</span>
|
||
<span class="sd"> options (optional dict): Additional information to specify how the environment is reset (optional,</span>
|
||
<span class="sd"> depending on the specific environment)</span>
|
||
|
||
<span class="sd"> Returns:</span>
|
||
<span class="sd"> observation (ObsType): Observation of the initial state. This will be an element of :attr:`observation_space`</span>
|
||
<span class="sd"> (typically a numpy array) and is analogous to the observation returned by :meth:`step`.</span>
|
||
<span class="sd"> info (dictionary): This dictionary contains auxiliary information complementing ``observation``. It should be analogous to</span>
|
||
<span class="sd"> the ``info`` returned by :meth:`step`.</span>
|
||
<span class="sd"> """</span>
|
||
<span class="c1"># Initialize the RNG if the seed is manually passed</span>
|
||
<span class="k">if</span> <span class="n">seed</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">_np_random</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_np_random_seed</span> <span class="o">=</span> <span class="n">seeding</span><span class="o">.</span><span class="n">np_random</span><span class="p">(</span><span class="n">seed</span><span class="p">)</span></div>
|
||
|
||
|
||
<div class="viewcode-block" id="Env.render">
|
||
<a class="viewcode-back" href="../../../api/env/#gymnasium.Env.render">[docs]</a>
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">render</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="n">RenderFrame</span> <span class="o">|</span> <span class="nb">list</span><span class="p">[</span><span class="n">RenderFrame</span><span class="p">]</span> <span class="o">|</span> <span class="kc">None</span><span class="p">:</span>
|
||
<span class="w"> </span><span class="sd">"""Compute the render frames as specified by :attr:`render_mode` during the initialization of the environment.</span>
|
||
|
||
<span class="sd"> The environment's :attr:`metadata` render modes (`env.metadata["render_modes"]`) should contain the possible</span>
|
||
<span class="sd"> ways to implement the render modes. In addition, list versions for most render modes is achieved through</span>
|
||
<span class="sd"> `gymnasium.make` which automatically applies a wrapper to collect rendered frames.</span>
|
||
|
||
<span class="sd"> Note:</span>
|
||
<span class="sd"> As the :attr:`render_mode` is known during ``__init__``, the objects used to render the environment state</span>
|
||
<span class="sd"> should be initialised in ``__init__``.</span>
|
||
|
||
<span class="sd"> By convention, if the :attr:`render_mode` is:</span>
|
||
|
||
<span class="sd"> - None (default): no render is computed.</span>
|
||
<span class="sd"> - "human": The environment is continuously rendered in the current display or terminal, usually for human consumption.</span>
|
||
<span class="sd"> This rendering should occur during :meth:`step` and :meth:`render` doesn't need to be called. Returns ``None``.</span>
|
||
<span class="sd"> - "rgb_array": Return a single frame representing the current state of the environment.</span>
|
||
<span class="sd"> A frame is a ``np.ndarray`` with shape ``(x, y, 3)`` representing RGB values for an x-by-y pixel image.</span>
|
||
<span class="sd"> - "ansi": Return a strings (``str``) or ``StringIO.StringIO`` containing a terminal-style text representation</span>
|
||
<span class="sd"> for each time step. The text can include newlines and ANSI escape sequences (e.g. for colors).</span>
|
||
<span class="sd"> - "rgb_array_list" and "ansi_list": List based version of render modes are possible (except Human) through the</span>
|
||
<span class="sd"> wrapper, :py:class:`gymnasium.wrappers.RenderCollection` that is automatically applied during ``gymnasium.make(..., render_mode="rgb_array_list")``.</span>
|
||
<span class="sd"> The frames collected are popped after :meth:`render` is called or :meth:`reset`.</span>
|
||
|
||
<span class="sd"> Note:</span>
|
||
<span class="sd"> Make sure that your class's :attr:`metadata` ``"render_modes"`` key includes the list of supported modes.</span>
|
||
|
||
<span class="sd"> .. versionchanged:: 0.25.0</span>
|
||
|
||
<span class="sd"> The render function was changed to no longer accept parameters, rather these parameters should be specified</span>
|
||
<span class="sd"> in the environment initialised, i.e., ``gymnasium.make("CartPole-v1", render_mode="human")``</span>
|
||
<span class="sd"> """</span>
|
||
<span class="k">raise</span> <span class="ne">NotImplementedError</span></div>
|
||
|
||
|
||
<div class="viewcode-block" id="Env.close">
|
||
<a class="viewcode-back" href="../../../api/env/#gymnasium.Env.close">[docs]</a>
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">close</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
||
<span class="w"> </span><span class="sd">"""After the user has finished using the environment, close contains the code necessary to "clean up" the environment.</span>
|
||
|
||
<span class="sd"> This is critical for closing rendering windows, database or HTTP connections.</span>
|
||
<span class="sd"> Calling ``close`` on an already closed environment has no effect and won't raise an error.</span>
|
||
<span class="sd"> """</span>
|
||
<span class="k">pass</span></div>
|
||
|
||
|
||
<span class="nd">@property</span>
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">unwrapped</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="n">Env</span><span class="p">[</span><span class="n">ObsType</span><span class="p">,</span> <span class="n">ActType</span><span class="p">]:</span>
|
||
<span class="w"> </span><span class="sd">"""Returns the base non-wrapped environment.</span>
|
||
|
||
<span class="sd"> Returns:</span>
|
||
<span class="sd"> Env: The base non-wrapped :class:`gymnasium.Env` instance</span>
|
||
<span class="sd"> """</span>
|
||
<span class="k">return</span> <span class="bp">self</span>
|
||
|
||
<span class="nd">@property</span>
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">np_random_seed</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="nb">int</span><span class="p">:</span>
|
||
<span class="w"> </span><span class="sd">"""Returns the environment's internal :attr:`_np_random_seed` that if not set will first initialise with a random int as seed.</span>
|
||
|
||
<span class="sd"> If :attr:`np_random_seed` was set directly instead of through :meth:`reset` or :meth:`set_np_random_through_seed`,</span>
|
||
<span class="sd"> the seed will take the value -1.</span>
|
||
|
||
<span class="sd"> Returns:</span>
|
||
<span class="sd"> int: the seed of the current `np_random` or -1, if the seed of the rng is unknown</span>
|
||
<span class="sd"> """</span>
|
||
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_np_random_seed</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">_np_random</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_np_random_seed</span> <span class="o">=</span> <span class="n">seeding</span><span class="o">.</span><span class="n">np_random</span><span class="p">()</span>
|
||
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_np_random_seed</span>
|
||
|
||
<span class="nd">@property</span>
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">np_random</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">Generator</span><span class="p">:</span>
|
||
<span class="w"> </span><span class="sd">"""Returns the environment's internal :attr:`_np_random` that if not set will initialise with a random seed.</span>
|
||
|
||
<span class="sd"> Returns:</span>
|
||
<span class="sd"> Instances of `np.random.Generator`</span>
|
||
<span class="sd"> """</span>
|
||
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_np_random</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">_np_random</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_np_random_seed</span> <span class="o">=</span> <span class="n">seeding</span><span class="o">.</span><span class="n">np_random</span><span class="p">()</span>
|
||
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_np_random</span>
|
||
|
||
<span class="nd">@np_random</span><span class="o">.</span><span class="n">setter</span>
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">np_random</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">value</span><span class="p">:</span> <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">Generator</span><span class="p">):</span>
|
||
<span class="w"> </span><span class="sd">"""Sets the environment's internal :attr:`_np_random` with the user-provided Generator.</span>
|
||
|
||
<span class="sd"> Since it is generally not possible to extract a seed from an instance of a random number generator,</span>
|
||
<span class="sd"> this will also set the :attr:`_np_random_seed` to `-1`, which is not valid as input for the creation</span>
|
||
<span class="sd"> of a numpy rng.</span>
|
||
<span class="sd"> """</span>
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">_np_random</span> <span class="o">=</span> <span class="n">value</span>
|
||
<span class="c1"># Setting a numpy rng with -1 will cause a ValueError</span>
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">_np_random_seed</span> <span class="o">=</span> <span class="o">-</span><span class="mi">1</span>
|
||
|
||
<span class="k">def</span><span class="w"> </span><span class="fm">__str__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
||
<span class="w"> </span><span class="sd">"""Returns a string of the environment with :attr:`spec` id's if :attr:`spec.</span>
|
||
|
||
<span class="sd"> Returns:</span>
|
||
<span class="sd"> A string identifying the environment</span>
|
||
<span class="sd"> """</span>
|
||
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">spec</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
|
||
<span class="k">return</span> <span class="sa">f</span><span class="s2">"<</span><span class="si">{</span><span class="nb">type</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="vm">__name__</span><span class="si">}</span><span class="s2"> instance>"</span>
|
||
<span class="k">else</span><span class="p">:</span>
|
||
<span class="k">return</span> <span class="sa">f</span><span class="s2">"<</span><span class="si">{</span><span class="nb">type</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="vm">__name__</span><span class="si">}</span><span class="s2"><</span><span class="si">{</span><span class="bp">self</span><span class="o">.</span><span class="n">spec</span><span class="o">.</span><span class="n">id</span><span class="si">}</span><span class="s2">>>"</span>
|
||
|
||
<span class="k">def</span><span class="w"> </span><span class="fm">__enter__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
||
<span class="w"> </span><span class="sd">"""Support with-statement for the environment."""</span>
|
||
<span class="k">return</span> <span class="bp">self</span>
|
||
|
||
<span class="k">def</span><span class="w"> </span><span class="fm">__exit__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="o">*</span><span class="n">args</span><span class="p">:</span> <span class="n">Any</span><span class="p">):</span>
|
||
<span class="w"> </span><span class="sd">"""Support with-statement for the environment and closes the environment."""</span>
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">close</span><span class="p">()</span>
|
||
<span class="c1"># propagate exception</span>
|
||
<span class="k">return</span> <span class="kc">False</span>
|
||
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">has_wrapper_attr</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">name</span><span class="p">:</span> <span class="nb">str</span><span class="p">)</span> <span class="o">-></span> <span class="nb">bool</span><span class="p">:</span>
|
||
<span class="w"> </span><span class="sd">"""Checks if the attribute `name` exists in the environment."""</span>
|
||
<span class="k">return</span> <span class="nb">hasattr</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">name</span><span class="p">)</span>
|
||
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">get_wrapper_attr</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">name</span><span class="p">:</span> <span class="nb">str</span><span class="p">)</span> <span class="o">-></span> <span class="n">Any</span><span class="p">:</span>
|
||
<span class="w"> </span><span class="sd">"""Gets the attribute `name` from the environment."""</span>
|
||
<span class="k">return</span> <span class="nb">getattr</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">name</span><span class="p">)</span>
|
||
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">set_wrapper_attr</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">name</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span> <span class="n">value</span><span class="p">:</span> <span class="n">Any</span><span class="p">,</span> <span class="o">*</span><span class="p">,</span> <span class="n">force</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">True</span><span class="p">)</span> <span class="o">-></span> <span class="nb">bool</span><span class="p">:</span>
|
||
<span class="w"> </span><span class="sd">"""Sets the attribute `name` on the environment with `value`, see `Wrapper.set_wrapper_attr` for more info."""</span>
|
||
<span class="k">if</span> <span class="n">force</span> <span class="ow">or</span> <span class="nb">hasattr</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">name</span><span class="p">):</span>
|
||
<span class="nb">setattr</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">name</span><span class="p">,</span> <span class="n">value</span><span class="p">)</span>
|
||
<span class="k">return</span> <span class="kc">True</span>
|
||
<span class="k">return</span> <span class="kc">False</span></div>
|
||
|
||
|
||
|
||
<span class="n">WrapperObsType</span> <span class="o">=</span> <span class="n">TypeVar</span><span class="p">(</span><span class="s2">"WrapperObsType"</span><span class="p">)</span>
|
||
<span class="n">WrapperActType</span> <span class="o">=</span> <span class="n">TypeVar</span><span class="p">(</span><span class="s2">"WrapperActType"</span><span class="p">)</span>
|
||
|
||
|
||
<div class="viewcode-block" id="Wrapper">
|
||
<a class="viewcode-back" href="../../../api/wrappers/#gymnasium.Wrapper">[docs]</a>
|
||
<span class="k">class</span><span class="w"> </span><span class="nc">Wrapper</span><span class="p">(</span>
|
||
<span class="n">Env</span><span class="p">[</span><span class="n">WrapperObsType</span><span class="p">,</span> <span class="n">WrapperActType</span><span class="p">],</span>
|
||
<span class="n">Generic</span><span class="p">[</span><span class="n">WrapperObsType</span><span class="p">,</span> <span class="n">WrapperActType</span><span class="p">,</span> <span class="n">ObsType</span><span class="p">,</span> <span class="n">ActType</span><span class="p">],</span>
|
||
<span class="p">):</span>
|
||
<span class="w"> </span><span class="sd">"""Wraps a :class:`gymnasium.Env` to allow a modular transformation of the :meth:`step` and :meth:`reset` methods.</span>
|
||
|
||
<span class="sd"> This class is the base class of all wrappers to change the behavior of the underlying environment.</span>
|
||
<span class="sd"> Wrappers that inherit from this class can modify the :attr:`action_space`, :attr:`observation_space`</span>
|
||
<span class="sd"> and :attr:`metadata` attributes, without changing the underlying environment's attributes.</span>
|
||
<span class="sd"> Moreover, the behavior of the :meth:`step` and :meth:`reset` methods can be changed by these wrappers.</span>
|
||
|
||
<span class="sd"> Some attributes (:attr:`spec`, :attr:`render_mode`, :attr:`np_random`) will point back to the wrapper's environment</span>
|
||
<span class="sd"> (i.e. to the corresponding attributes of :attr:`env`).</span>
|
||
|
||
<span class="sd"> Note:</span>
|
||
<span class="sd"> If you inherit from :class:`Wrapper`, don't forget to call ``super().__init__(env)``</span>
|
||
<span class="sd"> """</span>
|
||
|
||
<span class="k">def</span><span class="w"> </span><span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">env</span><span class="p">:</span> <span class="n">Env</span><span class="p">[</span><span class="n">ObsType</span><span class="p">,</span> <span class="n">ActType</span><span class="p">]):</span>
|
||
<span class="w"> </span><span class="sd">"""Wraps an environment to allow a modular transformation of the :meth:`step` and :meth:`reset` methods.</span>
|
||
|
||
<span class="sd"> Args:</span>
|
||
<span class="sd"> env: The environment to wrap</span>
|
||
<span class="sd"> """</span>
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">env</span> <span class="o">=</span> <span class="n">env</span>
|
||
<span class="k">assert</span> <span class="nb">isinstance</span><span class="p">(</span>
|
||
<span class="n">env</span><span class="p">,</span> <span class="n">Env</span>
|
||
<span class="p">),</span> <span class="sa">f</span><span class="s2">"Expected env to be a `gymnasium.Env` but got </span><span class="si">{</span><span class="nb">type</span><span class="p">(</span><span class="n">env</span><span class="p">)</span><span class="si">}</span><span class="s2">"</span>
|
||
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">_action_space</span><span class="p">:</span> <span class="n">spaces</span><span class="o">.</span><span class="n">Space</span><span class="p">[</span><span class="n">WrapperActType</span><span class="p">]</span> <span class="o">|</span> <span class="kc">None</span> <span class="o">=</span> <span class="kc">None</span>
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">_observation_space</span><span class="p">:</span> <span class="n">spaces</span><span class="o">.</span><span class="n">Space</span><span class="p">[</span><span class="n">WrapperObsType</span><span class="p">]</span> <span class="o">|</span> <span class="kc">None</span> <span class="o">=</span> <span class="kc">None</span>
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">_metadata</span><span class="p">:</span> <span class="nb">dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">Any</span><span class="p">]</span> <span class="o">|</span> <span class="kc">None</span> <span class="o">=</span> <span class="kc">None</span>
|
||
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">_cached_spec</span><span class="p">:</span> <span class="n">EnvSpec</span> <span class="o">|</span> <span class="kc">None</span> <span class="o">=</span> <span class="kc">None</span>
|
||
|
||
<div class="viewcode-block" id="Wrapper.step">
|
||
<a class="viewcode-back" href="../../../api/wrappers/#gymnasium.Wrapper.step">[docs]</a>
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">step</span><span class="p">(</span>
|
||
<span class="bp">self</span><span class="p">,</span> <span class="n">action</span><span class="p">:</span> <span class="n">WrapperActType</span>
|
||
<span class="p">)</span> <span class="o">-></span> <span class="nb">tuple</span><span class="p">[</span><span class="n">WrapperObsType</span><span class="p">,</span> <span class="n">SupportsFloat</span><span class="p">,</span> <span class="nb">bool</span><span class="p">,</span> <span class="nb">bool</span><span class="p">,</span> <span class="nb">dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">Any</span><span class="p">]]:</span>
|
||
<span class="w"> </span><span class="sd">"""Uses the :meth:`step` of the :attr:`env` that can be overwritten to change the returned data."""</span>
|
||
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">step</span><span class="p">(</span><span class="n">action</span><span class="p">)</span></div>
|
||
|
||
|
||
<div class="viewcode-block" id="Wrapper.reset">
|
||
<a class="viewcode-back" href="../../../api/wrappers/#gymnasium.Wrapper.reset">[docs]</a>
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">reset</span><span class="p">(</span>
|
||
<span class="bp">self</span><span class="p">,</span> <span class="o">*</span><span class="p">,</span> <span class="n">seed</span><span class="p">:</span> <span class="nb">int</span> <span class="o">|</span> <span class="kc">None</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span> <span class="n">options</span><span class="p">:</span> <span class="nb">dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">Any</span><span class="p">]</span> <span class="o">|</span> <span class="kc">None</span> <span class="o">=</span> <span class="kc">None</span>
|
||
<span class="p">)</span> <span class="o">-></span> <span class="nb">tuple</span><span class="p">[</span><span class="n">WrapperObsType</span><span class="p">,</span> <span class="nb">dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">Any</span><span class="p">]]:</span>
|
||
<span class="w"> </span><span class="sd">"""Uses the :meth:`reset` of the :attr:`env` that can be overwritten to change the returned data."""</span>
|
||
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">reset</span><span class="p">(</span><span class="n">seed</span><span class="o">=</span><span class="n">seed</span><span class="p">,</span> <span class="n">options</span><span class="o">=</span><span class="n">options</span><span class="p">)</span></div>
|
||
|
||
|
||
<div class="viewcode-block" id="Wrapper.render">
|
||
<a class="viewcode-back" href="../../../api/wrappers/#gymnasium.Wrapper.render">[docs]</a>
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">render</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="n">RenderFrame</span> <span class="o">|</span> <span class="nb">list</span><span class="p">[</span><span class="n">RenderFrame</span><span class="p">]</span> <span class="o">|</span> <span class="kc">None</span><span class="p">:</span>
|
||
<span class="w"> </span><span class="sd">"""Uses the :meth:`render` of the :attr:`env` that can be overwritten to change the returned data."""</span>
|
||
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">render</span><span class="p">()</span></div>
|
||
|
||
|
||
<div class="viewcode-block" id="Wrapper.close">
|
||
<a class="viewcode-back" href="../../../api/wrappers/#gymnasium.Wrapper.close">[docs]</a>
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">close</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
||
<span class="w"> </span><span class="sd">"""Closes the wrapper and :attr:`env`."""</span>
|
||
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">close</span><span class="p">()</span></div>
|
||
|
||
|
||
<span class="nd">@property</span>
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">np_random_seed</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="nb">int</span> <span class="o">|</span> <span class="kc">None</span><span class="p">:</span>
|
||
<span class="w"> </span><span class="sd">"""Returns the base environment's :attr:`np_random_seed`."""</span>
|
||
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">np_random_seed</span>
|
||
|
||
<span class="nd">@property</span>
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">unwrapped</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="n">Env</span><span class="p">[</span><span class="n">ObsType</span><span class="p">,</span> <span class="n">ActType</span><span class="p">]:</span>
|
||
<span class="w"> </span><span class="sd">"""Returns the base environment of the wrapper.</span>
|
||
|
||
<span class="sd"> This will be the bare :class:`gymnasium.Env` environment, underneath all layers of wrappers.</span>
|
||
<span class="sd"> """</span>
|
||
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">unwrapped</span>
|
||
|
||
<span class="nd">@property</span>
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">spec</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="n">EnvSpec</span> <span class="o">|</span> <span class="kc">None</span><span class="p">:</span>
|
||
<span class="w"> </span><span class="sd">"""Returns the :attr:`Env` :attr:`spec` attribute with the `WrapperSpec` if the wrapper inherits from `EzPickle`."""</span>
|
||
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_cached_spec</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
|
||
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_cached_spec</span>
|
||
|
||
<span class="n">env_spec</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">spec</span>
|
||
<span class="k">if</span> <span class="n">env_spec</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
|
||
<span class="c1"># See if the wrapper inherits from `RecordConstructorArgs` then add the kwargs otherwise use `None` for the wrapper kwargs. This will raise an error in `make`</span>
|
||
<span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">RecordConstructorArgs</span><span class="p">):</span>
|
||
<span class="n">kwargs</span> <span class="o">=</span> <span class="nb">getattr</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="s2">"_saved_kwargs"</span><span class="p">)</span>
|
||
<span class="k">if</span> <span class="s2">"env"</span> <span class="ow">in</span> <span class="n">kwargs</span><span class="p">:</span>
|
||
<span class="n">kwargs</span> <span class="o">=</span> <span class="n">deepcopy</span><span class="p">(</span><span class="n">kwargs</span><span class="p">)</span>
|
||
<span class="n">kwargs</span><span class="o">.</span><span class="n">pop</span><span class="p">(</span><span class="s2">"env"</span><span class="p">)</span>
|
||
<span class="k">else</span><span class="p">:</span>
|
||
<span class="n">kwargs</span> <span class="o">=</span> <span class="kc">None</span>
|
||
|
||
<span class="kn">from</span><span class="w"> </span><span class="nn">gymnasium.envs.registration</span><span class="w"> </span><span class="kn">import</span> <span class="n">WrapperSpec</span>
|
||
|
||
<span class="n">wrapper_spec</span> <span class="o">=</span> <span class="n">WrapperSpec</span><span class="p">(</span>
|
||
<span class="n">name</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">class_name</span><span class="p">(),</span>
|
||
<span class="n">entry_point</span><span class="o">=</span><span class="sa">f</span><span class="s2">"</span><span class="si">{</span><span class="bp">self</span><span class="o">.</span><span class="vm">__module__</span><span class="si">}</span><span class="s2">:</span><span class="si">{</span><span class="nb">type</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="vm">__name__</span><span class="si">}</span><span class="s2">"</span><span class="p">,</span>
|
||
<span class="n">kwargs</span><span class="o">=</span><span class="n">kwargs</span><span class="p">,</span>
|
||
<span class="p">)</span>
|
||
|
||
<span class="c1"># to avoid reference issues we deepcopy the prior environments spec and add the new information</span>
|
||
<span class="k">try</span><span class="p">:</span>
|
||
<span class="n">env_spec</span> <span class="o">=</span> <span class="n">deepcopy</span><span class="p">(</span><span class="n">env_spec</span><span class="p">)</span>
|
||
<span class="n">env_spec</span><span class="o">.</span><span class="n">additional_wrappers</span> <span class="o">+=</span> <span class="p">(</span><span class="n">wrapper_spec</span><span class="p">,)</span>
|
||
<span class="k">except</span> <span class="ne">Exception</span> <span class="k">as</span> <span class="n">e</span><span class="p">:</span>
|
||
<span class="n">gymnasium</span><span class="o">.</span><span class="n">logger</span><span class="o">.</span><span class="n">warn</span><span class="p">(</span>
|
||
<span class="sa">f</span><span class="s2">"An exception occurred (</span><span class="si">{</span><span class="n">e</span><span class="si">}</span><span class="s2">) while copying the environment spec=</span><span class="si">{</span><span class="n">env_spec</span><span class="si">}</span><span class="s2">"</span>
|
||
<span class="p">)</span>
|
||
<span class="k">return</span> <span class="kc">None</span>
|
||
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">_cached_spec</span> <span class="o">=</span> <span class="n">env_spec</span>
|
||
<span class="k">return</span> <span class="n">env_spec</span>
|
||
|
||
<div class="viewcode-block" id="Wrapper.wrapper_spec">
|
||
<a class="viewcode-back" href="../../../api/wrappers/#gymnasium.Wrapper.wrapper_spec">[docs]</a>
|
||
<span class="nd">@classmethod</span>
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">wrapper_spec</span><span class="p">(</span><span class="bp">cls</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">:</span> <span class="n">Any</span><span class="p">)</span> <span class="o">-></span> <span class="n">WrapperSpec</span><span class="p">:</span>
|
||
<span class="w"> </span><span class="sd">"""Generates a `WrapperSpec` for the wrappers."""</span>
|
||
<span class="kn">from</span><span class="w"> </span><span class="nn">gymnasium.envs.registration</span><span class="w"> </span><span class="kn">import</span> <span class="n">WrapperSpec</span>
|
||
|
||
<span class="k">return</span> <span class="n">WrapperSpec</span><span class="p">(</span>
|
||
<span class="n">name</span><span class="o">=</span><span class="bp">cls</span><span class="o">.</span><span class="n">class_name</span><span class="p">(),</span>
|
||
<span class="n">entry_point</span><span class="o">=</span><span class="sa">f</span><span class="s2">"</span><span class="si">{</span><span class="bp">cls</span><span class="o">.</span><span class="vm">__module__</span><span class="si">}</span><span class="s2">:</span><span class="si">{</span><span class="bp">cls</span><span class="o">.</span><span class="vm">__name__</span><span class="si">}</span><span class="s2">"</span><span class="p">,</span>
|
||
<span class="n">kwargs</span><span class="o">=</span><span class="n">kwargs</span><span class="p">,</span>
|
||
<span class="p">)</span></div>
|
||
|
||
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">has_wrapper_attr</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">name</span><span class="p">:</span> <span class="nb">str</span><span class="p">)</span> <span class="o">-></span> <span class="nb">bool</span><span class="p">:</span>
|
||
<span class="w"> </span><span class="sd">"""Checks if the given attribute is within the wrapper or its environment."""</span>
|
||
<span class="k">if</span> <span class="nb">hasattr</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">name</span><span class="p">):</span>
|
||
<span class="k">return</span> <span class="kc">True</span>
|
||
<span class="k">else</span><span class="p">:</span>
|
||
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">has_wrapper_attr</span><span class="p">(</span><span class="n">name</span><span class="p">)</span>
|
||
|
||
<div class="viewcode-block" id="Wrapper.get_wrapper_attr">
|
||
<a class="viewcode-back" href="../../../api/wrappers/#gymnasium.Wrapper.get_wrapper_attr">[docs]</a>
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">get_wrapper_attr</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">name</span><span class="p">:</span> <span class="nb">str</span><span class="p">)</span> <span class="o">-></span> <span class="n">Any</span><span class="p">:</span>
|
||
<span class="w"> </span><span class="sd">"""Gets an attribute from the wrapper and lower environments if `name` doesn't exist in this object.</span>
|
||
|
||
<span class="sd"> Args:</span>
|
||
<span class="sd"> name: The variable name to get</span>
|
||
|
||
<span class="sd"> Returns:</span>
|
||
<span class="sd"> The variable with name in wrapper or lower environments</span>
|
||
<span class="sd"> """</span>
|
||
<span class="k">if</span> <span class="nb">hasattr</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">name</span><span class="p">):</span>
|
||
<span class="k">return</span> <span class="nb">getattr</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">name</span><span class="p">)</span>
|
||
<span class="k">else</span><span class="p">:</span>
|
||
<span class="k">try</span><span class="p">:</span>
|
||
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">get_wrapper_attr</span><span class="p">(</span><span class="n">name</span><span class="p">)</span>
|
||
<span class="k">except</span> <span class="ne">AttributeError</span> <span class="k">as</span> <span class="n">e</span><span class="p">:</span>
|
||
<span class="k">raise</span> <span class="ne">AttributeError</span><span class="p">(</span>
|
||
<span class="sa">f</span><span class="s2">"wrapper </span><span class="si">{</span><span class="bp">self</span><span class="o">.</span><span class="n">class_name</span><span class="p">()</span><span class="si">}</span><span class="s2"> has no attribute </span><span class="si">{</span><span class="n">name</span><span class="si">!r}</span><span class="s2">"</span>
|
||
<span class="p">)</span> <span class="kn">from</span><span class="w"> </span><span class="nn">e</span></div>
|
||
|
||
|
||
<div class="viewcode-block" id="Wrapper.set_wrapper_attr">
|
||
<a class="viewcode-back" href="../../../api/wrappers/#gymnasium.Wrapper.set_wrapper_attr">[docs]</a>
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">set_wrapper_attr</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">name</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span> <span class="n">value</span><span class="p">:</span> <span class="n">Any</span><span class="p">,</span> <span class="o">*</span><span class="p">,</span> <span class="n">force</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">True</span><span class="p">)</span> <span class="o">-></span> <span class="nb">bool</span><span class="p">:</span>
|
||
<span class="w"> </span><span class="sd">"""Sets an attribute on this wrapper or lower environment if `name` is already defined.</span>
|
||
|
||
<span class="sd"> Args:</span>
|
||
<span class="sd"> name: The variable name</span>
|
||
<span class="sd"> value: The new variable value</span>
|
||
<span class="sd"> force: Whether to create the attribute on this wrapper if it does not exists on the</span>
|
||
<span class="sd"> lower environment instead of raising an exception</span>
|
||
|
||
<span class="sd"> Returns:</span>
|
||
<span class="sd"> If the variable has been set in this or a lower wrapper.</span>
|
||
<span class="sd"> """</span>
|
||
<span class="k">if</span> <span class="nb">hasattr</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">name</span><span class="p">):</span>
|
||
<span class="nb">setattr</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">name</span><span class="p">,</span> <span class="n">value</span><span class="p">)</span>
|
||
<span class="k">return</span> <span class="kc">True</span>
|
||
<span class="k">else</span><span class="p">:</span>
|
||
<span class="n">already_set</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">set_wrapper_attr</span><span class="p">(</span><span class="n">name</span><span class="p">,</span> <span class="n">value</span><span class="p">,</span> <span class="n">force</span><span class="o">=</span><span class="kc">False</span><span class="p">)</span>
|
||
<span class="k">if</span> <span class="n">already_set</span><span class="p">:</span>
|
||
<span class="k">return</span> <span class="kc">True</span>
|
||
<span class="k">elif</span> <span class="n">force</span><span class="p">:</span>
|
||
<span class="nb">setattr</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">name</span><span class="p">,</span> <span class="n">value</span><span class="p">)</span>
|
||
<span class="k">return</span> <span class="kc">True</span>
|
||
<span class="k">else</span><span class="p">:</span>
|
||
<span class="k">return</span> <span class="kc">False</span></div>
|
||
|
||
|
||
<span class="k">def</span><span class="w"> </span><span class="fm">__str__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
||
<span class="w"> </span><span class="sd">"""Returns the wrapper name and the :attr:`env` representation string."""</span>
|
||
<span class="k">return</span> <span class="sa">f</span><span class="s2">"<</span><span class="si">{</span><span class="nb">type</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="vm">__name__</span><span class="si">}{</span><span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="si">}</span><span class="s2">>"</span>
|
||
|
||
<span class="k">def</span><span class="w"> </span><span class="fm">__repr__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
||
<span class="w"> </span><span class="sd">"""Returns the string representation of the wrapper."""</span>
|
||
<span class="k">return</span> <span class="nb">str</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span>
|
||
|
||
<span class="nd">@classmethod</span>
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">class_name</span><span class="p">(</span><span class="bp">cls</span><span class="p">)</span> <span class="o">-></span> <span class="nb">str</span><span class="p">:</span>
|
||
<span class="w"> </span><span class="sd">"""Returns the class name of the wrapper."""</span>
|
||
<span class="k">return</span> <span class="bp">cls</span><span class="o">.</span><span class="vm">__name__</span>
|
||
|
||
<span class="nd">@property</span>
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">action_space</span><span class="p">(</span>
|
||
<span class="bp">self</span><span class="p">,</span>
|
||
<span class="p">)</span> <span class="o">-></span> <span class="n">spaces</span><span class="o">.</span><span class="n">Space</span><span class="p">[</span><span class="n">ActType</span><span class="p">]</span> <span class="o">|</span> <span class="n">spaces</span><span class="o">.</span><span class="n">Space</span><span class="p">[</span><span class="n">WrapperActType</span><span class="p">]:</span>
|
||
<span class="w"> </span><span class="sd">"""Return the :attr:`Env` :attr:`action_space` unless overwritten then the wrapper :attr:`action_space` is used."""</span>
|
||
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_action_space</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
|
||
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">action_space</span>
|
||
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_action_space</span>
|
||
|
||
<span class="nd">@action_space</span><span class="o">.</span><span class="n">setter</span>
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">action_space</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">space</span><span class="p">:</span> <span class="n">spaces</span><span class="o">.</span><span class="n">Space</span><span class="p">[</span><span class="n">WrapperActType</span><span class="p">]):</span>
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">_action_space</span> <span class="o">=</span> <span class="n">space</span>
|
||
|
||
<span class="nd">@property</span>
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">observation_space</span><span class="p">(</span>
|
||
<span class="bp">self</span><span class="p">,</span>
|
||
<span class="p">)</span> <span class="o">-></span> <span class="n">spaces</span><span class="o">.</span><span class="n">Space</span><span class="p">[</span><span class="n">ObsType</span><span class="p">]</span> <span class="o">|</span> <span class="n">spaces</span><span class="o">.</span><span class="n">Space</span><span class="p">[</span><span class="n">WrapperObsType</span><span class="p">]:</span>
|
||
<span class="w"> </span><span class="sd">"""Return the :attr:`Env` :attr:`observation_space` unless overwritten then the wrapper :attr:`observation_space` is used."""</span>
|
||
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_observation_space</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
|
||
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">observation_space</span>
|
||
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_observation_space</span>
|
||
|
||
<span class="nd">@observation_space</span><span class="o">.</span><span class="n">setter</span>
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">observation_space</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">space</span><span class="p">:</span> <span class="n">spaces</span><span class="o">.</span><span class="n">Space</span><span class="p">[</span><span class="n">WrapperObsType</span><span class="p">]):</span>
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">_observation_space</span> <span class="o">=</span> <span class="n">space</span>
|
||
|
||
<span class="nd">@property</span>
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">metadata</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="nb">dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">Any</span><span class="p">]:</span>
|
||
<span class="w"> </span><span class="sd">"""Returns the :attr:`Env` :attr:`metadata`."""</span>
|
||
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_metadata</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
|
||
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">metadata</span>
|
||
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_metadata</span>
|
||
|
||
<span class="nd">@metadata</span><span class="o">.</span><span class="n">setter</span>
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">metadata</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">value</span><span class="p">:</span> <span class="nb">dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">Any</span><span class="p">]):</span>
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">_metadata</span> <span class="o">=</span> <span class="n">value</span>
|
||
|
||
<span class="nd">@property</span>
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">render_mode</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="nb">str</span> <span class="o">|</span> <span class="kc">None</span><span class="p">:</span>
|
||
<span class="w"> </span><span class="sd">"""Returns the :attr:`Env` :attr:`render_mode`."""</span>
|
||
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">render_mode</span>
|
||
|
||
<span class="nd">@property</span>
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">np_random</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">Generator</span><span class="p">:</span>
|
||
<span class="w"> </span><span class="sd">"""Returns the :attr:`Env` :attr:`np_random` attribute."""</span>
|
||
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">np_random</span>
|
||
|
||
<span class="nd">@np_random</span><span class="o">.</span><span class="n">setter</span>
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">np_random</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">value</span><span class="p">:</span> <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">Generator</span><span class="p">):</span>
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">np_random</span> <span class="o">=</span> <span class="n">value</span>
|
||
|
||
<span class="nd">@property</span>
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">_np_random</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
||
<span class="w"> </span><span class="sd">"""This code will never be run due to __getattr__ being called prior this.</span>
|
||
|
||
<span class="sd"> It seems that @property overwrites the variable (`_np_random`) meaning that __getattr__ gets called with the missing variable.</span>
|
||
<span class="sd"> """</span>
|
||
<span class="k">raise</span> <span class="ne">AttributeError</span><span class="p">(</span>
|
||
<span class="s2">"Can't access `_np_random` of a wrapper, use `.unwrapped._np_random` or `.np_random`."</span>
|
||
<span class="p">)</span></div>
|
||
|
||
|
||
|
||
<div class="viewcode-block" id="ObservationWrapper">
|
||
<a class="viewcode-back" href="../../../api/wrappers/observation_wrappers/#gymnasium.ObservationWrapper">[docs]</a>
|
||
<span class="k">class</span><span class="w"> </span><span class="nc">ObservationWrapper</span><span class="p">(</span><span class="n">Wrapper</span><span class="p">[</span><span class="n">WrapperObsType</span><span class="p">,</span> <span class="n">ActType</span><span class="p">,</span> <span class="n">ObsType</span><span class="p">,</span> <span class="n">ActType</span><span class="p">]):</span>
|
||
<span class="w"> </span><span class="sd">"""Modify observations from :meth:`Env.reset` and :meth:`Env.step` using :meth:`observation` function.</span>
|
||
|
||
<span class="sd"> If you would like to apply a function to only the observation before</span>
|
||
<span class="sd"> passing it to the learning code, you can simply inherit from :class:`ObservationWrapper` and overwrite the method</span>
|
||
<span class="sd"> :meth:`observation` to implement that transformation. The transformation defined in that method must be</span>
|
||
<span class="sd"> reflected by the :attr:`env` observation space. Otherwise, you need to specify the new observation space of the</span>
|
||
<span class="sd"> wrapper by setting :attr:`self.observation_space` in the :meth:`__init__` method of your wrapper.</span>
|
||
<span class="sd"> """</span>
|
||
|
||
<span class="k">def</span><span class="w"> </span><span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">env</span><span class="p">:</span> <span class="n">Env</span><span class="p">[</span><span class="n">ObsType</span><span class="p">,</span> <span class="n">ActType</span><span class="p">]):</span>
|
||
<span class="w"> </span><span class="sd">"""Constructor for the observation wrapper.</span>
|
||
|
||
<span class="sd"> Args:</span>
|
||
<span class="sd"> env: Environment to be wrapped.</span>
|
||
<span class="sd"> """</span>
|
||
<span class="n">Wrapper</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">env</span><span class="p">)</span>
|
||
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">reset</span><span class="p">(</span>
|
||
<span class="bp">self</span><span class="p">,</span> <span class="o">*</span><span class="p">,</span> <span class="n">seed</span><span class="p">:</span> <span class="nb">int</span> <span class="o">|</span> <span class="kc">None</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span> <span class="n">options</span><span class="p">:</span> <span class="nb">dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">Any</span><span class="p">]</span> <span class="o">|</span> <span class="kc">None</span> <span class="o">=</span> <span class="kc">None</span>
|
||
<span class="p">)</span> <span class="o">-></span> <span class="nb">tuple</span><span class="p">[</span><span class="n">WrapperObsType</span><span class="p">,</span> <span class="nb">dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">Any</span><span class="p">]]:</span>
|
||
<span class="w"> </span><span class="sd">"""Modifies the :attr:`env` after calling :meth:`reset`, returning a modified observation using :meth:`self.observation`."""</span>
|
||
<span class="n">obs</span><span class="p">,</span> <span class="n">info</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">reset</span><span class="p">(</span><span class="n">seed</span><span class="o">=</span><span class="n">seed</span><span class="p">,</span> <span class="n">options</span><span class="o">=</span><span class="n">options</span><span class="p">)</span>
|
||
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">observation</span><span class="p">(</span><span class="n">obs</span><span class="p">),</span> <span class="n">info</span>
|
||
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">step</span><span class="p">(</span>
|
||
<span class="bp">self</span><span class="p">,</span> <span class="n">action</span><span class="p">:</span> <span class="n">ActType</span>
|
||
<span class="p">)</span> <span class="o">-></span> <span class="nb">tuple</span><span class="p">[</span><span class="n">WrapperObsType</span><span class="p">,</span> <span class="n">SupportsFloat</span><span class="p">,</span> <span class="nb">bool</span><span class="p">,</span> <span class="nb">bool</span><span class="p">,</span> <span class="nb">dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">Any</span><span class="p">]]:</span>
|
||
<span class="w"> </span><span class="sd">"""Modifies the :attr:`env` after calling :meth:`step` using :meth:`self.observation` on the returned observations."""</span>
|
||
<span class="n">observation</span><span class="p">,</span> <span class="n">reward</span><span class="p">,</span> <span class="n">terminated</span><span class="p">,</span> <span class="n">truncated</span><span class="p">,</span> <span class="n">info</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">step</span><span class="p">(</span><span class="n">action</span><span class="p">)</span>
|
||
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">observation</span><span class="p">(</span><span class="n">observation</span><span class="p">),</span> <span class="n">reward</span><span class="p">,</span> <span class="n">terminated</span><span class="p">,</span> <span class="n">truncated</span><span class="p">,</span> <span class="n">info</span>
|
||
|
||
<div class="viewcode-block" id="ObservationWrapper.observation">
|
||
<a class="viewcode-back" href="../../../api/wrappers/observation_wrappers/#gymnasium.ObservationWrapper.observation">[docs]</a>
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">observation</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">observation</span><span class="p">:</span> <span class="n">ObsType</span><span class="p">)</span> <span class="o">-></span> <span class="n">WrapperObsType</span><span class="p">:</span>
|
||
<span class="w"> </span><span class="sd">"""Returns a modified observation.</span>
|
||
|
||
<span class="sd"> Args:</span>
|
||
<span class="sd"> observation: The :attr:`env` observation</span>
|
||
|
||
<span class="sd"> Returns:</span>
|
||
<span class="sd"> The modified observation</span>
|
||
<span class="sd"> """</span>
|
||
<span class="k">raise</span> <span class="ne">NotImplementedError</span></div>
|
||
</div>
|
||
|
||
|
||
|
||
<div class="viewcode-block" id="RewardWrapper">
|
||
<a class="viewcode-back" href="../../../api/wrappers/reward_wrappers/#gymnasium.RewardWrapper">[docs]</a>
|
||
<span class="k">class</span><span class="w"> </span><span class="nc">RewardWrapper</span><span class="p">(</span><span class="n">Wrapper</span><span class="p">[</span><span class="n">ObsType</span><span class="p">,</span> <span class="n">ActType</span><span class="p">,</span> <span class="n">ObsType</span><span class="p">,</span> <span class="n">ActType</span><span class="p">]):</span>
|
||
<span class="w"> </span><span class="sd">"""Superclass of wrappers that can modify the returning reward from a step.</span>
|
||
|
||
<span class="sd"> If you would like to apply a function to the reward that is returned by the base environment before</span>
|
||
<span class="sd"> passing it to learning code, you can simply inherit from :class:`RewardWrapper` and overwrite the method</span>
|
||
<span class="sd"> :meth:`reward` to implement that transformation.</span>
|
||
<span class="sd"> """</span>
|
||
|
||
<span class="k">def</span><span class="w"> </span><span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">env</span><span class="p">:</span> <span class="n">Env</span><span class="p">[</span><span class="n">ObsType</span><span class="p">,</span> <span class="n">ActType</span><span class="p">]):</span>
|
||
<span class="w"> </span><span class="sd">"""Constructor for the Reward wrapper.</span>
|
||
|
||
<span class="sd"> Args:</span>
|
||
<span class="sd"> env: Environment to be wrapped.</span>
|
||
<span class="sd"> """</span>
|
||
<span class="n">Wrapper</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">env</span><span class="p">)</span>
|
||
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">step</span><span class="p">(</span>
|
||
<span class="bp">self</span><span class="p">,</span> <span class="n">action</span><span class="p">:</span> <span class="n">ActType</span>
|
||
<span class="p">)</span> <span class="o">-></span> <span class="nb">tuple</span><span class="p">[</span><span class="n">ObsType</span><span class="p">,</span> <span class="n">SupportsFloat</span><span class="p">,</span> <span class="nb">bool</span><span class="p">,</span> <span class="nb">bool</span><span class="p">,</span> <span class="nb">dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">Any</span><span class="p">]]:</span>
|
||
<span class="w"> </span><span class="sd">"""Modifies the :attr:`env` :meth:`step` reward using :meth:`self.reward`."""</span>
|
||
<span class="n">observation</span><span class="p">,</span> <span class="n">reward</span><span class="p">,</span> <span class="n">terminated</span><span class="p">,</span> <span class="n">truncated</span><span class="p">,</span> <span class="n">info</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">step</span><span class="p">(</span><span class="n">action</span><span class="p">)</span>
|
||
<span class="k">return</span> <span class="n">observation</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">reward</span><span class="p">(</span><span class="n">reward</span><span class="p">),</span> <span class="n">terminated</span><span class="p">,</span> <span class="n">truncated</span><span class="p">,</span> <span class="n">info</span>
|
||
|
||
<div class="viewcode-block" id="RewardWrapper.reward">
|
||
<a class="viewcode-back" href="../../../api/wrappers/reward_wrappers/#gymnasium.RewardWrapper.reward">[docs]</a>
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">reward</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">reward</span><span class="p">:</span> <span class="n">SupportsFloat</span><span class="p">)</span> <span class="o">-></span> <span class="n">SupportsFloat</span><span class="p">:</span>
|
||
<span class="w"> </span><span class="sd">"""Returns a modified environment ``reward``.</span>
|
||
|
||
<span class="sd"> Args:</span>
|
||
<span class="sd"> reward: The :attr:`env` :meth:`step` reward</span>
|
||
|
||
<span class="sd"> Returns:</span>
|
||
<span class="sd"> The modified `reward`</span>
|
||
<span class="sd"> """</span>
|
||
<span class="k">raise</span> <span class="ne">NotImplementedError</span></div>
|
||
</div>
|
||
|
||
|
||
|
||
<div class="viewcode-block" id="ActionWrapper">
|
||
<a class="viewcode-back" href="../../../api/wrappers/action_wrappers/#gymnasium.ActionWrapper">[docs]</a>
|
||
<span class="k">class</span><span class="w"> </span><span class="nc">ActionWrapper</span><span class="p">(</span><span class="n">Wrapper</span><span class="p">[</span><span class="n">ObsType</span><span class="p">,</span> <span class="n">WrapperActType</span><span class="p">,</span> <span class="n">ObsType</span><span class="p">,</span> <span class="n">ActType</span><span class="p">]):</span>
|
||
<span class="w"> </span><span class="sd">"""Superclass of wrappers that can modify the action before :meth:`step`.</span>
|
||
|
||
<span class="sd"> If you would like to apply a function to the action before passing it to the base environment,</span>
|
||
<span class="sd"> you can simply inherit from :class:`ActionWrapper` and overwrite the method :meth:`action` to implement</span>
|
||
<span class="sd"> that transformation. The transformation defined in that method must take values in the base environment’s</span>
|
||
<span class="sd"> action space. However, its domain might differ from the original action space.</span>
|
||
<span class="sd"> In that case, you need to specify the new action space of the wrapper by setting :attr:`action_space` in</span>
|
||
<span class="sd"> the :meth:`__init__` method of your wrapper.</span>
|
||
|
||
<span class="sd"> Among others, Gymnasium provides the action wrappers :class:`gymnasium.wrappers.ClipAction` and</span>
|
||
<span class="sd"> :class:`gymnasium.wrappers.RescaleAction` for clipping and rescaling actions.</span>
|
||
<span class="sd"> """</span>
|
||
|
||
<span class="k">def</span><span class="w"> </span><span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">env</span><span class="p">:</span> <span class="n">Env</span><span class="p">[</span><span class="n">ObsType</span><span class="p">,</span> <span class="n">ActType</span><span class="p">]):</span>
|
||
<span class="w"> </span><span class="sd">"""Constructor for the action wrapper.</span>
|
||
|
||
<span class="sd"> Args:</span>
|
||
<span class="sd"> env: Environment to be wrapped.</span>
|
||
<span class="sd"> """</span>
|
||
<span class="n">Wrapper</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">env</span><span class="p">)</span>
|
||
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">step</span><span class="p">(</span>
|
||
<span class="bp">self</span><span class="p">,</span> <span class="n">action</span><span class="p">:</span> <span class="n">WrapperActType</span>
|
||
<span class="p">)</span> <span class="o">-></span> <span class="nb">tuple</span><span class="p">[</span><span class="n">ObsType</span><span class="p">,</span> <span class="n">SupportsFloat</span><span class="p">,</span> <span class="nb">bool</span><span class="p">,</span> <span class="nb">bool</span><span class="p">,</span> <span class="nb">dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">Any</span><span class="p">]]:</span>
|
||
<span class="w"> </span><span class="sd">"""Runs the :attr:`env` :meth:`env.step` using the modified ``action`` from :meth:`self.action`."""</span>
|
||
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">step</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">action</span><span class="p">(</span><span class="n">action</span><span class="p">))</span>
|
||
|
||
<div class="viewcode-block" id="ActionWrapper.action">
|
||
<a class="viewcode-back" href="../../../api/wrappers/action_wrappers/#gymnasium.ActionWrapper.action">[docs]</a>
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">action</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">action</span><span class="p">:</span> <span class="n">WrapperActType</span><span class="p">)</span> <span class="o">-></span> <span class="n">ActType</span><span class="p">:</span>
|
||
<span class="w"> </span><span class="sd">"""Returns a modified action before :meth:`step` is called.</span>
|
||
|
||
<span class="sd"> Args:</span>
|
||
<span class="sd"> action: The original :meth:`step` actions</span>
|
||
|
||
<span class="sd"> Returns:</span>
|
||
<span class="sd"> The modified actions</span>
|
||
<span class="sd"> """</span>
|
||
<span class="k">raise</span> <span class="ne">NotImplementedError</span></div>
|
||
</div>
|
||
|
||
</pre></div>
|
||
</article>
|
||
</div>
|
||
<footer>
|
||
|
||
<div class="related-pages">
|
||
|
||
|
||
</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 no-toc">
|
||
|
||
|
||
|
||
</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=151cd43d"></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>
|
||
|
||
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> |