Files
Gymnasium/v1.0.0a1/_modules/gymnasium/wrappers/stateful_observation/index.html

1413 lines
124 KiB
HTML
Raw Normal View History

<!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/wrappers/stateful_observation.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/wrappers/stateful_observation.html" />
<link rel="shortcut icon" href="../../../../_static/favicon.png"/><!-- Generated with Sphinx 7.2.6 and Furo 2023.08.19.dev1 -->
<title>gymnasium.wrappers.stateful_observation - Gymnasium Documentation</title>
<link rel="stylesheet" type="text/css" href="../../../../_static/pygments.css?v=a746c00c" />
<link rel="stylesheet" type="text/css" href="../../../../_static/styles/furo.css?v=3e7f4c72" />
<link rel="stylesheet" type="text/css" href="../../../../_static/sg_gallery.css?v=61a4c737" />
<link rel="stylesheet" type="text/css" href="../../../../_static/sg_gallery-binder.css?v=f4aeca0c" />
<link rel="stylesheet" type="text/css" href="../../../../_static/sg_gallery-dataframe.css?v=2082cf3c" />
<link rel="stylesheet" type="text/css" href="../../../../_static/sg_gallery-rendered-html.css?v=1277b6f3" />
<link rel="stylesheet" type="text/css" href="../../../../_static/styles/furo-extensions.css?v=49cbaffd" />
<style>
body {
--color-code-background: #f8f8f8;
--color-code-foreground: black;
}
@media not print {
body[data-theme="dark"] {
--color-code-background: #202020;
--color-code-foreground: #d0d0d0;
}
@media (prefers-color-scheme: dark) {
body:not([data-theme="light"]) {
--color-code-background: #202020;
--color-code-foreground: #d0d0d0;
}
}
}
</style></head>
<body>
<header class="farama-header" aria-label="Farama header">
<div class="farama-header__container">
<div class="farama-header__left--mobile">
<label class="nav-overlay-icon" for="__navigation">
<div class="visually-hidden">Toggle site navigation sidebar</div>
<svg viewBox="0 0 24 24" xmlns="http://www.w3.org/2000/svg">
<defs></defs>
<line x1="0.5" y1="4" x2="23.5" y2="4"></line>
<line x1="0.232" y1="12" x2="23.5" y2="12"></line>
<line x1="0.232" y1="20" x2="23.5" y2="20"></line>
</svg>
</label>
</div>
<div class="farama-header__left farama-header__center--mobile">
<a href="../../../../">
<img class="farama-header__logo only-light" src="../../../../_static/img/gymnasium_black.svg" alt="Light Logo"/>
<img class="farama-header__logo only-dark" src="../../../../_static/img/gymnasium_white.svg" alt="Dark Logo"/>
<span class="farama-header__title">Gymnasium Documentation</span>
</a>
</div>
<div class="farama-header__right">
<div class="farama-header-menu">
<button class="farama-header-menu__btn" aria-label="Open Farama Menu" aria-expanded="false" aria-haspopup="true" aria-controls="farama-menu">
<img class="farama-black-logo-invert" src="../../../../_static/img/farama-logo-header.svg">
<svg viewBox="0 0 24 24" viewBox="0 0 24 24" xmlns="http://www.w3.org/2000/svg">
<polyline style="stroke-linecap: round; stroke-linejoin: round; fill: none; stroke-width: 2px;" points="1 7 12 18 23 7"></polyline>
</svg>
</button>
<div class="farama-header-menu-container farama-hidden" aria-hidden="true" id="farama-menu">
<div class="farama-header-menu__header">
<a href="https://farama.org">
<img class="farama-header-menu__logo farama-white-logo-invert" src="../../../../_static/img/farama_solid_white.svg" alt="Farama Foundation logo">
<span>Farama Foundation</span>
</a>
<div class="farama-header-menu-header__right">
<button id="farama-close-menu">
<svg viewBox="0 0 24 24" xmlns="http://www.w3.org/2000/svg" fill="none" stroke="currentColor"
stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="icon-close">
<line x1="3" y1="21" x2="21" y2="3"></line>
<line x1="3" y1="3" x2="21" y2="21"></line>
</svg>
</button>
</div>
</div>
<div class="farama-header-menu__body">
<!-- Response from farama.org/api/projects.json -->
</div>
</div>
</div>
</div>
</div>
</header>
<script>
document.body.dataset.theme = localStorage.getItem("theme") || "auto";
</script>
<svg xmlns="http://www.w3.org/2000/svg" style="display: none;">
<symbol id="svg-toc" viewBox="0 0 24 24">
<title>Contents</title>
<svg stroke="currentColor" fill="currentColor" stroke-width="0" viewBox="0 0 1024 1024">
<path d="M408 442h480c4.4 0 8-3.6 8-8v-56c0-4.4-3.6-8-8-8H408c-4.4 0-8 3.6-8 8v56c0 4.4 3.6 8 8 8zm-8 204c0 4.4 3.6 8 8 8h480c4.4 0 8-3.6 8-8v-56c0-4.4-3.6-8-8-8H408c-4.4 0-8 3.6-8 8v56zm504-486H120c-4.4 0-8 3.6-8 8v56c0 4.4 3.6 8 8 8h784c4.4 0 8-3.6 8-8v-56c0-4.4-3.6-8-8-8zm0 632H120c-4.4 0-8 3.6-8 8v56c0 4.4 3.6 8 8 8h784c4.4 0 8-3.6 8-8v-56c0-4.4-3.6-8-8-8zM115.4 518.9L271.7 642c5.8 4.6 14.4.5 14.4-6.9V388.9c0-7.4-8.5-11.5-14.4-6.9L115.4 505.1a8.74 8.74 0 0 0 0 13.8z"/>
</svg>
</symbol>
<symbol id="svg-menu" viewBox="0 0 24 24">
<title>Menu</title>
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24" fill="none" stroke="currentColor"
stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="feather-menu">
<line x1="3" y1="12" x2="21" y2="12"></line>
<line x1="3" y1="6" x2="21" y2="6"></line>
<line x1="3" y1="18" x2="21" y2="18"></line>
</svg>
</symbol>
<symbol id="svg-arrow-right" viewBox="0 0 24 24">
<title>Expand</title>
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24" fill="none" stroke="currentColor"
stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="feather-chevron-right">
<polyline points="9 18 15 12 9 6"></polyline>
</svg>
</symbol>
<symbol id="svg-sun" viewBox="0 0 24 24">
<title>Light mode</title>
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24" fill="none" stroke="currentColor"
stroke-width="1.5" stroke-linecap="round" stroke-linejoin="round" class="feather-sun">
<circle cx="12" cy="12" r="5"></circle>
<line x1="12" y1="1" x2="12" y2="3"></line>
<line x1="12" y1="21" x2="12" y2="23"></line>
<line x1="4.22" y1="4.22" x2="5.64" y2="5.64"></line>
<line x1="18.36" y1="18.36" x2="19.78" y2="19.78"></line>
<line x1="1" y1="12" x2="3" y2="12"></line>
<line x1="21" y1="12" x2="23" y2="12"></line>
<line x1="4.22" y1="19.78" x2="5.64" y2="18.36"></line>
<line x1="18.36" y1="5.64" x2="19.78" y2="4.22"></line>
</svg>
</symbol>
<symbol id="svg-moon" viewBox="0 0 24 24">
<title>Dark mode</title>
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24" fill="none" stroke="currentColor"
stroke-width="1.5" stroke-linecap="round" stroke-linejoin="round" class="icon-tabler-moon">
<path stroke="none" d="M0 0h24v24H0z" fill="none" />
<path d="M12 3c.132 0 .263 0 .393 0a7.5 7.5 0 0 0 7.92 12.446a9 9 0 1 1 -8.313 -12.454z" />
</svg>
</symbol>
<symbol id="svg-sun-half" viewBox="0 0 24 24">
<title>Auto light/dark mode</title>
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24" fill="none" stroke="currentColor"
stroke-width="1.5" stroke-linecap="round" stroke-linejoin="round" class="icon-tabler-shadow">
<path stroke="none" d="M0 0h24v24H0z" fill="none"/>
<circle cx="12" cy="12" r="9" />
<path d="M13 12h5" />
<path d="M13 15h4" />
<path d="M13 18h1" />
<path d="M13 9h4" />
<path d="M13 6h1" />
</svg>
</symbol>
</svg>
<input type="checkbox" class="sidebar-toggle" name="__navigation" id="__navigation">
<input type="checkbox" class="sidebar-toggle" name="__toc" id="__toc">
<label class="overlay sidebar-overlay" for="__navigation">
<div class="visually-hidden">Hide navigation sidebar</div>
</label>
<label class="overlay toc-overlay" for="__toc">
<div class="visually-hidden">Hide table of contents sidebar</div>
</label>
<div class="page">
<!--<header class="mobile-header">
<div class="header-left">
<label class="nav-overlay-icon" for="__navigation">
<div class="visually-hidden">Toggle site navigation sidebar</div>
<i class="icon"><svg><use href="#svg-menu"></use></svg></i>
</label>
</div>
<div class="header-center">
<a href="../../../../"><div class="brand">Gymnasium Documentation</div></a>
</div>
<div class="header-right">
<div class="theme-toggle-container theme-toggle-header">
<button class="theme-toggle">
<div class="visually-hidden">Toggle Light / Dark / Auto color theme</div>
<svg class="theme-icon-when-auto"><use href="#svg-sun-half"></use></svg>
<svg class="theme-icon-when-dark"><use href="#svg-moon"></use></svg>
<svg class="theme-icon-when-light"><use href="#svg-sun"></use></svg>
</button>
</div>
<label class="toc-overlay-icon toc-header-icon 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>
<li class="toctree-l2"><a class="reference internal" href="../../../../api/vector/utils/">Utility functions</a></li>
</ul>
</li>
<li class="toctree-l1 has-children"><a class="reference internal" href="../../../../api/wrappers/">Wrappers</a><input class="toctree-checkbox" id="toctree-checkbox-2" name="toctree-checkbox-2" role="switch" type="checkbox"/><label for="toctree-checkbox-2"><div class="visually-hidden">Toggle navigation of Wrappers</div><i class="icon"><svg><use href="#svg-arrow-right"></use></svg></i></label><ul>
<li class="toctree-l2"><a class="reference internal" href="../../../../api/wrappers/table/">List of Wrappers</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../api/wrappers/misc_wrappers/">Misc Wrappers</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../api/wrappers/action_wrappers/">Action Wrappers</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../api/wrappers/observation_wrappers/">Observation Wrappers</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../api/wrappers/reward_wrappers/">Reward Wrappers</a></li>
</ul>
</li>
<li class="toctree-l1 has-children"><a class="reference internal" href="../../../../api/vector/">Vectorize</a><input class="toctree-checkbox" id="toctree-checkbox-3" name="toctree-checkbox-3" role="switch" type="checkbox"/><label for="toctree-checkbox-3"><div class="visually-hidden">Toggle navigation of Vectorize</div><i class="icon"><svg><use href="#svg-arrow-right"></use></svg></i></label><ul>
<li class="toctree-l2"><a class="reference internal" href="../../../../api/vector/wrappers/">Wrappers</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../api/vector/async_vector_env/">AsyncVectorEnv</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../api/vector/sync_vector_env/">SyncVectorEnv</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../api/vector/utils/">Utility functions</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="../../../../api/utils/">Utility functions</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../api/functional/">Functional Env</a></li>
</ul>
<p class="caption" role="heading"><span class="caption-text">Environments</span></p>
<ul>
<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 has-children"><a class="reference internal" href="../../../../environments/atari/">Atari</a><input class="toctree-checkbox" id="toctree-checkbox-8" name="toctree-checkbox-8" role="switch" type="checkbox"/><label for="toctree-checkbox-8"><div class="visually-hidden">Toggle navigation of Atari</div><i class="icon"><svg><use href="#svg-arrow-right"></use></svg></i></label><ul>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/adventure/">Adventure</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/air_raid/">AirRaid</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/alien/">Alien</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/amidar/">Amidar</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/assault/">Assault</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/asterix/">Asterix</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/asteroids/">Asteroids</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/atlantis/">Atlantis</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/atlantis2/">Atlantis2</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/backgammon/">Backgammon</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/bank_heist/">BankHeist</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/basic_math/">BasicMath</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/battle_zone/">BattleZone</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/beam_rider/">BeamRider</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/berzerk/">Berzerk</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/blackjack/">Blackjack</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/bowling/">Bowling</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/boxing/">Boxing</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/breakout/">Breakout</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/carnival/">Carnival</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/casino/">Casino</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/centipede/">Centipede</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/chopper_command/">ChopperCommand</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/crazy_climber/">CrazyClimber</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/crossbow/">Crossbow</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/darkchambers/">Darkchambers</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/defender/">Defender</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/demon_attack/">DemonAttack</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/donkey_kong/">DonkeyKong</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/double_dunk/">DoubleDunk</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/earthworld/">Earthworld</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/elevator_action/">ElevatorAction</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/enduro/">Enduro</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/entombed/">Entombed</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/et/">Et</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/fishing_derby/">FishingDerby</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/flag_capture/">FlagCapture</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/freeway/">Freeway</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/frogger/">Frogger</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/frostbite/">Frostbite</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/galaxian/">Galaxian</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/gopher/">Gopher</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/gravitar/">Gravitar</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/hangman/">Hangman</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/haunted_house/">HauntedHouse</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/hero/">Hero</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/human_cannonball/">HumanCannonball</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/ice_hockey/">IceHockey</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/jamesbond/">Jamesbond</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/journey_escape/">JourneyEscape</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/kaboom/">Kaboom</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/kangaroo/">Kangaroo</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/keystone_kapers/">KeystoneKapers</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/king_kong/">KingKong</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/klax/">Klax</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/koolaid/">Koolaid</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/krull/">Krull</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/kung_fu_master/">KungFuMaster</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/laser_gates/">LaserGates</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/lost_luggage/">LostLuggage</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/mario_bros/">MarioBros</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/miniature_golf/">MiniatureGolf</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/montezuma_revenge/">MontezumaRevenge</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/mr_do/">MrDo</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/ms_pacman/">MsPacman</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/name_this_game/">NameThisGame</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/othello/">Othello</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/pacman/">Pacman</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/phoenix/">Phoenix</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/pitfall/">Pitfall</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/pitfall2/">Pitfall2</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/pong/">Pong</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/pooyan/">Pooyan</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/private_eye/">PrivateEye</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/qbert/">Qbert</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/riverraid/">Riverraid</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/road_runner/">RoadRunner</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/robotank/">Robotank</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/seaquest/">Seaquest</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/sir_lancelot/">SirLancelot</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/skiing/">Skiing</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/solaris/">Solaris</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/space_invaders/">SpaceInvaders</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/space_war/">SpaceWar</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/star_gunner/">StarGunner</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/superman/">Superman</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/surround/">Surround</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/tennis/">Tennis</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/tetris/">Tetris</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/tic_tac_toe_3d/">TicTacToe3D</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/time_pilot/">TimePilot</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/trondead/">Trondead</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/turmoil/">Turmoil</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/tutankham/">Tutankham</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/up_n_down/">UpNDown</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/venture/">Venture</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/video_checkers/">VideoCheckers</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/video_chess/">VideoChess</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/video_cube/">VideoCube</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/video_pinball/">VideoPinball</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/wizard_of_wor/">WizardOfWor</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/word_zapper/">WordZapper</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/yars_revenge/">YarsRevenge</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../environments/atari/zaxxon/">Zaxxon</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="../../../../environments/third_party_environments/">Third-Party Environments</a></li>
</ul>
<p class="caption" role="heading"><span class="caption-text">Tutorials</span></p>
<ul>
<li class="toctree-l1 has-children"><a class="reference internal" href="../../../../tutorials/gymnasium_basics/">Gymnasium Basics</a><input class="toctree-checkbox" id="toctree-checkbox-9" name="toctree-checkbox-9" role="switch" type="checkbox"/><label for="toctree-checkbox-9"><div class="visually-hidden">Toggle navigation of Gymnasium Basics</div><i class="icon"><svg><use href="#svg-arrow-right"></use></svg></i></label><ul>
<li class="toctree-l2"><a class="reference internal" href="../../../../tutorials/gymnasium_basics/handling_time_limits/">Handling Time Limits</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../tutorials/gymnasium_basics/implementing_custom_wrappers/">Implementing Custom Wrappers</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../tutorials/gymnasium_basics/environment_creation/">Make your own custom environment</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../tutorials/gymnasium_basics/vector_envs_tutorial/">Training A2C with Vector Envs and Domain Randomization</a></li>
</ul>
</li>
<li class="toctree-l1 has-children"><a class="reference internal" href="../../../../tutorials/training_agents/">Training Agents</a><input class="toctree-checkbox" id="toctree-checkbox-10" name="toctree-checkbox-10" role="switch" type="checkbox"/><label for="toctree-checkbox-10"><div class="visually-hidden">Toggle navigation of Training Agents</div><i class="icon"><svg><use href="#svg-arrow-right"></use></svg></i></label><ul>
<li class="toctree-l2"><a class="reference internal" href="../../../../tutorials/training_agents/reinforce_invpend_gym_v26/">Training using REINFORCE for Mujoco</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../tutorials/training_agents/blackjack_tutorial/">Solving Blackjack with Q-Learning</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../tutorials/training_agents/FrozenLake_tuto/">Frozenlake benchmark</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="../../../../tutorials/third-party-tutorials/">Third-Party Tutorials</a></li>
<li class="toctree-l1"><a class="reference external" href="https://www.comet.com/docs/v2/integrations/ml-frameworks/gymnasium/?utm_source=gymnasium&amp;utm_medium=partner&amp;utm_campaign=partner_gymnasium_2023&amp;utm_content=docs_gymnasium">Comet Tutorial</a></li>
</ul>
<p class="caption" role="heading"><span class="caption-text">Development</span></p>
<ul>
<li class="toctree-l1"><a class="reference external" href="https://github.com/Farama-Foundation/Gymnasium">Github</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../gymnasium_release_notes/">Gymnasium Release Notes</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../gym_release_notes/">Gym Release Notes</a></li>
<li class="toctree-l1"><a class="reference external" href="https://github.com/Farama-Foundation/Gymnasium/blob/main/docs/README.md">Contribute to the Docs</a></li>
</ul>
</div>
</div>
</div>
</div>
</aside>
<div class="main-container">
<div class="main">
<div class="content">
<div class="article-container">
<a href="#" class="back-to-top muted-link">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24">
<path d="M13 20h-2V8l-5.5 5.5-1.42-1.42L12 4.16l7.92 7.92-1.42 1.42L13 8v12z"></path>
</svg>
<span>Back to top</span>
</a>
<div class="content-icon-container"><div class="theme-toggle-container theme-toggle-content">
<button class="theme-toggle" title="Toggle color theme">
<div class="visually-hidden">Toggle Light / Dark / Auto color theme</div>
<svg class="theme-icon-when-auto">
<use href="#svg-sun-half"></use>
</svg>
<svg class="theme-icon-when-dark">
<use href="#svg-moon"></use>
</svg>
<svg class="theme-icon-when-light">
<use href="#svg-sun"></use>
</svg>
</button>
</div>
<label class="toc-overlay-icon toc-content-icon 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.wrappers.stateful_observation</h1><div class="highlight"><pre>
<span></span><span class="sd">&quot;&quot;&quot;A collection of stateful observation wrappers.</span>
<span class="sd">* ``DelayObservation`` - A wrapper for delaying the returned observation</span>
<span class="sd">* ``TimeAwareObservation`` - A wrapper for adding time aware observations to environment observation</span>
<span class="sd">* ``FrameStackObservation`` - Frame stack the observations</span>
<span class="sd">* ``NormalizeObservation`` - Normalized the observations to have unit variance with a moving mean</span>
<span class="sd">* ``MaxAndSkipObservation`` - Return only every ``skip``-th frame (frameskipping) and return the max between the two last frames.</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="kn">from</span> <span class="nn">__future__</span> <span class="kn">import</span> <span class="n">annotations</span>
<span class="kn">from</span> <span class="nn">collections</span> <span class="kn">import</span> <span class="n">deque</span>
<span class="kn">from</span> <span class="nn">copy</span> <span class="kn">import</span> <span class="n">deepcopy</span>
<span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">Any</span><span class="p">,</span> <span class="n">Final</span><span class="p">,</span> <span class="n">SupportsFloat</span>
<span class="kn">import</span> <span class="nn">numpy</span> <span class="k">as</span> <span class="nn">np</span>
<span class="kn">import</span> <span class="nn">gymnasium</span> <span class="k">as</span> <span class="nn">gym</span>
<span class="kn">import</span> <span class="nn">gymnasium.spaces</span> <span class="k">as</span> <span class="nn">spaces</span>
<span class="kn">from</span> <span class="nn">gymnasium.core</span> <span class="kn">import</span> <span class="n">ActType</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">WrapperObsType</span>
<span class="kn">from</span> <span class="nn">gymnasium.spaces</span> <span class="kn">import</span> <span class="n">Box</span><span class="p">,</span> <span class="n">Dict</span><span class="p">,</span> <span class="n">Tuple</span>
<span class="kn">from</span> <span class="nn">gymnasium.vector.utils</span> <span class="kn">import</span> <span class="n">batch_space</span><span class="p">,</span> <span class="n">concatenate</span><span class="p">,</span> <span class="n">create_empty_array</span>
<span class="kn">from</span> <span class="nn">gymnasium.wrappers.utils</span> <span class="kn">import</span> <span class="n">RunningMeanStd</span><span class="p">,</span> <span class="n">create_zero_array</span>
<span class="n">__all__</span> <span class="o">=</span> <span class="p">[</span>
<span class="s2">&quot;DelayObservation&quot;</span><span class="p">,</span>
<span class="s2">&quot;TimeAwareObservation&quot;</span><span class="p">,</span>
<span class="s2">&quot;FrameStackObservation&quot;</span><span class="p">,</span>
<span class="s2">&quot;NormalizeObservation&quot;</span><span class="p">,</span>
<span class="s2">&quot;MaxAndSkipObservation&quot;</span><span class="p">,</span>
<span class="p">]</span>
<div class="viewcode-block" id="DelayObservation">
<a class="viewcode-back" href="../../../../api/wrappers/observation_wrappers/#gymnasium.wrappers.DelayObservation">[docs]</a>
<span class="k">class</span> <span class="nc">DelayObservation</span><span class="p">(</span>
<span class="n">gym</span><span class="o">.</span><span class="n">ObservationWrapper</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">gym</span><span class="o">.</span><span class="n">utils</span><span class="o">.</span><span class="n">RecordConstructorArgs</span>
<span class="p">):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;Adds a delay to the returned observation from the environment.</span>
<span class="sd"> Before reaching the :attr:`delay` number of timesteps, returned observations is an array of zeros with</span>
<span class="sd"> the same shape as the observation space.</span>
<span class="sd"> No vector version of the wrapper exists.</span>
<span class="sd"> Note:</span>
<span class="sd"> This does not support random delay values, if users are interested, please raise an issue or pull request to add this feature.</span>
<span class="sd"> Example:</span>
<span class="sd"> &gt;&gt;&gt; import gymnasium as gym</span>
<span class="sd"> &gt;&gt;&gt; env = gym.make(&quot;CartPole-v1&quot;)</span>
<span class="sd"> &gt;&gt;&gt; env.reset(seed=123)</span>
<span class="sd"> (array([ 0.01823519, -0.0446179 , -0.02796401, -0.03156282], dtype=float32), {})</span>
<span class="sd"> &gt;&gt;&gt; env = DelayObservation(env, delay=2)</span>
<span class="sd"> &gt;&gt;&gt; env.reset(seed=123)</span>
<span class="sd"> (array([0., 0., 0., 0.], dtype=float32), {})</span>
<span class="sd"> &gt;&gt;&gt; env.step(env.action_space.sample())</span>
<span class="sd"> (array([0., 0., 0., 0.], dtype=float32), 1.0, False, False, {})</span>
<span class="sd"> &gt;&gt;&gt; env.step(env.action_space.sample())</span>
<span class="sd"> (array([ 0.01823519, -0.0446179 , -0.02796401, -0.03156282], dtype=float32), 1.0, False, False, {})</span>
<span class="sd"> Change logs:</span>
<span class="sd"> * v1.0.0 - Initially added</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">def</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">gym</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="n">delay</span><span class="p">:</span> <span class="nb">int</span><span class="p">):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;Initialises the DelayObservation wrapper with an integer.</span>
<span class="sd"> Args:</span>
<span class="sd"> env: The environment to wrap</span>
<span class="sd"> delay: The number of timesteps to delay observations</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">np</span><span class="o">.</span><span class="n">issubdtype</span><span class="p">(</span><span class="nb">type</span><span class="p">(</span><span class="n">delay</span><span class="p">),</span> <span class="n">np</span><span class="o">.</span><span class="n">integer</span><span class="p">):</span>
<span class="k">raise</span> <span class="ne">TypeError</span><span class="p">(</span>
<span class="sa">f</span><span class="s2">&quot;The delay is expected to be an integer, actual type: </span><span class="si">{</span><span class="nb">type</span><span class="p">(</span><span class="n">delay</span><span class="p">)</span><span class="si">}</span><span class="s2">&quot;</span>
<span class="p">)</span>
<span class="k">if</span> <span class="ow">not</span> <span class="mi">0</span> <span class="o">&lt;=</span> <span class="n">delay</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span>
<span class="sa">f</span><span class="s2">&quot;The delay needs to be greater than zero, actual value: </span><span class="si">{</span><span class="n">delay</span><span class="si">}</span><span class="s2">&quot;</span>
<span class="p">)</span>
<span class="n">gym</span><span class="o">.</span><span class="n">utils</span><span class="o">.</span><span class="n">RecordConstructorArgs</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">delay</span><span class="o">=</span><span class="n">delay</span><span class="p">)</span>
<span class="n">gym</span><span class="o">.</span><span class="n">ObservationWrapper</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="bp">self</span><span class="o">.</span><span class="n">delay</span><span class="p">:</span> <span class="n">Final</span><span class="p">[</span><span class="nb">int</span><span class="p">]</span> <span class="o">=</span> <span class="nb">int</span><span class="p">(</span><span class="n">delay</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">observation_queue</span><span class="p">:</span> <span class="n">Final</span><span class="p">[</span><span class="n">deque</span><span class="p">]</span> <span class="o">=</span> <span class="n">deque</span><span class="p">()</span>
<span class="k">def</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">-&gt;</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="w"> </span><span class="sd">&quot;&quot;&quot;Resets the environment, clearing the observation queue.&quot;&quot;&quot;</span>
<span class="bp">self</span><span class="o">.</span><span class="n">observation_queue</span><span class="o">.</span><span class="n">clear</span><span class="p">()</span>
<span class="k">return</span> <span class="nb">super</span><span class="p">()</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">def</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">-&gt;</span> <span class="n">ObsType</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;Return the delayed observation.&quot;&quot;&quot;</span>
<span class="bp">self</span><span class="o">.</span><span class="n">observation_queue</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">observation</span><span class="p">)</span>
<span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">observation_queue</span><span class="p">)</span> <span class="o">&gt;</span> <span class="bp">self</span><span class="o">.</span><span class="n">delay</span><span class="p">:</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">observation_queue</span><span class="o">.</span><span class="n">popleft</span><span class="p">()</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">return</span> <span class="n">create_zero_array</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">observation_space</span><span class="p">)</span></div>
<div class="viewcode-block" id="TimeAwareObservation">
<a class="viewcode-back" href="../../../../api/wrappers/observation_wrappers/#gymnasium.wrappers.TimeAwareObservation">[docs]</a>
<span class="k">class</span> <span class="nc">TimeAwareObservation</span><span class="p">(</span>
<span class="n">gym</span><span class="o">.</span><span class="n">ObservationWrapper</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">gym</span><span class="o">.</span><span class="n">utils</span><span class="o">.</span><span class="n">RecordConstructorArgs</span><span class="p">,</span>
<span class="p">):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;Augment the observation with the number of time steps taken within an episode.</span>
<span class="sd"> The :attr:`normalize_time` if ``True`` represents time as a normalized value between [0,1]</span>
<span class="sd"> otherwise if ``False``, the current timestep is an integer.</span>
<span class="sd"> For environments with ``Dict`` observation spaces, the time information is automatically</span>
<span class="sd"> added in the key `&quot;time&quot;` (can be changed through :attr:`dict_time_key`) and for environments with ``Tuple``</span>
<span class="sd"> observation space, the time information is added as the final element in the tuple.</span>
<span class="sd"> Otherwise, the observation space is transformed into a ``Dict`` observation space with two keys,</span>
<span class="sd"> `&quot;obs&quot;` for the base environment&#39;s observation and `&quot;time&quot;` for the time information.</span>
<span class="sd"> To flatten the observation, use the :attr:`flatten` parameter which will use the</span>
<span class="sd"> :func:`gymnasium.spaces.utils.flatten` function.</span>
<span class="sd"> No vector version of the wrapper exists.</span>
<span class="sd"> Example:</span>
<span class="sd"> &gt;&gt;&gt; import gymnasium as gym</span>
<span class="sd"> &gt;&gt;&gt; from gymnasium.wrappers import TimeAwareObservation</span>
<span class="sd"> &gt;&gt;&gt; env = gym.make(&quot;CartPole-v1&quot;)</span>
<span class="sd"> &gt;&gt;&gt; env = TimeAwareObservation(env)</span>
<span class="sd"> &gt;&gt;&gt; env.observation_space</span>
<span class="sd"> Box([-4.80000019e+00 -3.40282347e+38 -4.18879032e-01 -3.40282347e+38</span>
<span class="sd"> 0.00000000e+00], [4.80000019e+00 3.40282347e+38 4.18879032e-01 3.40282347e+38</span>
<span class="sd"> 5.00000000e+02], (5,), float64)</span>
<span class="sd"> &gt;&gt;&gt; env.reset(seed=42)[0]</span>
<span class="sd"> array([ 0.0273956 , -0.00611216, 0.03585979, 0.0197368 , 0. ])</span>
<span class="sd"> &gt;&gt;&gt; _ = env.action_space.seed(42)</span>
<span class="sd"> &gt;&gt;&gt; env.step(env.action_space.sample())[0]</span>
<span class="sd"> array([ 0.02727336, -0.20172954, 0.03625453, 0.32351476, 1. ])</span>
<span class="sd"> Normalize time observation space example:</span>
<span class="sd"> &gt;&gt;&gt; env = gym.make(&#39;CartPole-v1&#39;)</span>
<span class="sd"> &gt;&gt;&gt; env = TimeAwareObservation(env, normalize_time=True)</span>
<span class="sd"> &gt;&gt;&gt; env.observation_space</span>
<span class="sd"> Box([-4.8000002e+00 -3.4028235e+38 -4.1887903e-01 -3.4028235e+38</span>
<span class="sd"> 0.0000000e+00], [4.8000002e+00 3.4028235e+38 4.1887903e-01 3.4028235e+38 1.0000000e+00], (5,), float32)</span>
<span class="sd"> &gt;&gt;&gt; env.reset(seed=42)[0]</span>
<span class="sd"> array([ 0.0273956 , -0.00611216, 0.03585979, 0.0197368 , 0. ],</span>
<span class="sd"> dtype=float32)</span>
<span class="sd"> &gt;&gt;&gt; _ = env.action_space.seed(42)</span>
<span class="sd"> &gt;&gt;&gt; env.step(env.action_space.sample())[0]</span>
<span class="sd"> array([ 0.02727336, -0.20172954, 0.03625453, 0.32351476, 0.002 ],</span>
<span class="sd"> dtype=float32)</span>
<span class="sd"> Flatten observation space example:</span>
<span class="sd"> &gt;&gt;&gt; env = gym.make(&quot;CartPole-v1&quot;)</span>
<span class="sd"> &gt;&gt;&gt; env = TimeAwareObservation(env, flatten=False)</span>
<span class="sd"> &gt;&gt;&gt; env.observation_space</span>
<span class="sd"> Dict(&#39;obs&#39;: Box([-4.8000002e+00 -3.4028235e+38 -4.1887903e-01 -3.4028235e+38], [4.8000002e+00 3.4028235e+38 4.1887903e-01 3.4028235e+38], (4,), float32), &#39;time&#39;: Box(0, 500, (1,), int32))</span>
<span class="sd"> &gt;&gt;&gt; env.reset(seed=42)[0]</span>
<span class="sd"> {&#39;obs&#39;: array([ 0.0273956 , -0.00611216, 0.03585979, 0.0197368 ], dtype=float32), &#39;time&#39;: array([0], dtype=int32)}</span>
<span class="sd"> &gt;&gt;&gt; _ = env.action_space.seed(42)</span>
<span class="sd"> &gt;&gt;&gt; env.step(env.action_space.sample())[0]</span>
<span class="sd"> {&#39;obs&#39;: array([ 0.02727336, -0.20172954, 0.03625453, 0.32351476], dtype=float32), &#39;time&#39;: array([1], dtype=int32)}</span>
<span class="sd"> Change logs:</span>
<span class="sd"> * v0.18.0 - Initially added</span>
<span class="sd"> * v1.0.0 - Remove vector environment support, add ``flatten`` and ``normalize_time`` parameters</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">def</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">gym</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="n">flatten</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="n">normalize_time</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">False</span><span class="p">,</span>
<span class="o">*</span><span class="p">,</span>
<span class="n">dict_time_key</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;time&quot;</span><span class="p">,</span>
<span class="p">):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;Initialize :class:`TimeAwareObservation`.</span>
<span class="sd"> Args:</span>
<span class="sd"> env: The environment to apply the wrapper</span>
<span class="sd"> flatten: Flatten the observation to a `Box` of a single dimension</span>
<span class="sd"> normalize_time: if `True` return time in the range [0,1]</span>
<span class="sd"> otherwise return time as remaining timesteps before truncation</span>
<span class="sd"> dict_time_key: For environment with a ``Dict`` observation space, the key for the time space. By default, `&quot;time&quot;`.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">gym</span><span class="o">.</span><span class="n">utils</span><span class="o">.</span><span class="n">RecordConstructorArgs</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">flatten</span><span class="o">=</span><span class="n">flatten</span><span class="p">,</span>
<span class="n">normalize_time</span><span class="o">=</span><span class="n">normalize_time</span><span class="p">,</span>
<span class="n">dict_time_key</span><span class="o">=</span><span class="n">dict_time_key</span><span class="p">,</span>
<span class="p">)</span>
<span class="n">gym</span><span class="o">.</span><span class="n">ObservationWrapper</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="bp">self</span><span class="o">.</span><span class="n">flatten</span><span class="p">:</span> <span class="n">Final</span><span class="p">[</span><span class="nb">bool</span><span class="p">]</span> <span class="o">=</span> <span class="n">flatten</span>
<span class="bp">self</span><span class="o">.</span><span class="n">normalize_time</span><span class="p">:</span> <span class="n">Final</span><span class="p">[</span><span class="nb">bool</span><span class="p">]</span> <span class="o">=</span> <span class="n">normalize_time</span>
<span class="c1"># We don&#39;t need to keep if a TimeLimit wrapper exists as `spec` will do that work for us now</span>
<span class="k">if</span> <span class="n">env</span><span class="o">.</span><span class="n">spec</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> <span class="ow">and</span> <span class="n">env</span><span class="o">.</span><span class="n">spec</span><span class="o">.</span><span class="n">max_episode_steps</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">max_timesteps</span> <span class="o">=</span> <span class="n">env</span><span class="o">.</span><span class="n">spec</span><span class="o">.</span><span class="n">max_episode_steps</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span>
<span class="s2">&quot;The environment must be wrapped by a TimeLimit wrapper or the spec specify a `max_episode_steps`.&quot;</span>
<span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">timesteps</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">0</span>
<span class="c1"># Find the normalized time space</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">normalize_time</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_time_preprocess_func</span> <span class="o">=</span> <span class="k">lambda</span> <span class="n">time</span><span class="p">:</span> <span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">(</span>
<span class="p">[</span><span class="n">time</span> <span class="o">/</span> <span class="bp">self</span><span class="o">.</span><span class="n">max_timesteps</span><span class="p">],</span> <span class="n">dtype</span><span class="o">=</span><span class="n">np</span><span class="o">.</span><span class="n">float32</span>
<span class="p">)</span>
<span class="n">time_space</span> <span class="o">=</span> <span class="n">Box</span><span class="p">(</span><span class="mf">0.0</span><span class="p">,</span> <span class="mf">1.0</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_time_preprocess_func</span> <span class="o">=</span> <span class="k">lambda</span> <span class="n">time</span><span class="p">:</span> <span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">([</span><span class="n">time</span><span class="p">],</span> <span class="n">dtype</span><span class="o">=</span><span class="n">np</span><span class="o">.</span><span class="n">int32</span><span class="p">)</span>
<span class="n">time_space</span> <span class="o">=</span> <span class="n">Box</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">max_timesteps</span><span class="p">,</span> <span class="n">dtype</span><span class="o">=</span><span class="n">np</span><span class="o">.</span><span class="n">int32</span><span class="p">)</span>
<span class="c1"># Find the observation space</span>
<span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">env</span><span class="o">.</span><span class="n">observation_space</span><span class="p">,</span> <span class="n">Dict</span><span class="p">):</span>
<span class="k">assert</span> <span class="n">dict_time_key</span> <span class="ow">not</span> <span class="ow">in</span> <span class="n">env</span><span class="o">.</span><span class="n">observation_space</span><span class="o">.</span><span class="n">keys</span><span class="p">()</span>
<span class="n">observation_space</span> <span class="o">=</span> <span class="n">Dict</span><span class="p">(</span>
<span class="p">{</span><span class="n">dict_time_key</span><span class="p">:</span> <span class="n">time_space</span><span class="p">,</span> <span class="o">**</span><span class="n">env</span><span class="o">.</span><span class="n">observation_space</span><span class="o">.</span><span class="n">spaces</span><span class="p">}</span>
<span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_append_data_func</span> <span class="o">=</span> <span class="k">lambda</span> <span class="n">obs</span><span class="p">,</span> <span class="n">time</span><span class="p">:</span> <span class="p">{</span><span class="n">dict_time_key</span><span class="p">:</span> <span class="n">time</span><span class="p">,</span> <span class="o">**</span><span class="n">obs</span><span class="p">}</span>
<span class="k">elif</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">env</span><span class="o">.</span><span class="n">observation_space</span><span class="p">,</span> <span class="n">Tuple</span><span class="p">):</span>
<span class="n">observation_space</span> <span class="o">=</span> <span class="n">Tuple</span><span class="p">(</span><span class="n">env</span><span class="o">.</span><span class="n">observation_space</span><span class="o">.</span><span class="n">spaces</span> <span class="o">+</span> <span class="p">(</span><span class="n">time_space</span><span class="p">,))</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_append_data_func</span> <span class="o">=</span> <span class="k">lambda</span> <span class="n">obs</span><span class="p">,</span> <span class="n">time</span><span class="p">:</span> <span class="n">obs</span> <span class="o">+</span> <span class="p">(</span><span class="n">time</span><span class="p">,)</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">observation_space</span> <span class="o">=</span> <span class="n">Dict</span><span class="p">(</span><span class="n">obs</span><span class="o">=</span><span class="n">env</span><span class="o">.</span><span class="n">observation_space</span><span class="p">,</span> <span class="n">time</span><span class="o">=</span><span class="n">time_space</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_append_data_func</span> <span class="o">=</span> <span class="k">lambda</span> <span class="n">obs</span><span class="p">,</span> <span class="n">time</span><span class="p">:</span> <span class="p">{</span><span class="s2">&quot;obs&quot;</span><span class="p">:</span> <span class="n">obs</span><span class="p">,</span> <span class="s2">&quot;time&quot;</span><span class="p">:</span> <span class="n">time</span><span class="p">}</span>
<span class="c1"># If to flatten the observation space</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">flatten</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">observation_space</span><span class="p">:</span> <span class="n">gym</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="n">spaces</span><span class="o">.</span><span class="n">flatten_space</span><span class="p">(</span>
<span class="n">observation_space</span>
<span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_obs_postprocess_func</span> <span class="o">=</span> <span class="k">lambda</span> <span class="n">obs</span><span class="p">:</span> <span class="n">spaces</span><span class="o">.</span><span class="n">flatten</span><span class="p">(</span>
<span class="n">observation_space</span><span class="p">,</span> <span class="n">obs</span>
<span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">observation_space</span><span class="p">:</span> <span class="n">gym</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="n">observation_space</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_obs_postprocess_func</span> <span class="o">=</span> <span class="k">lambda</span> <span class="n">obs</span><span class="p">:</span> <span class="n">obs</span>
<span class="k">def</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">-&gt;</span> <span class="n">WrapperObsType</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;Adds to the observation with the current time information.</span>
<span class="sd"> Args:</span>
<span class="sd"> observation: The observation to add the time step to</span>
<span class="sd"> Returns:</span>
<span class="sd"> The observation with the time information appended to it</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_obs_postprocess_func</span><span class="p">(</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_append_data_func</span><span class="p">(</span>
<span class="n">observation</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_time_preprocess_func</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">timesteps</span><span class="p">)</span>
<span class="p">)</span>
<span class="p">)</span>
<span class="k">def</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">-&gt;</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">&quot;&quot;&quot;Steps through the environment, incrementing the time step.</span>
<span class="sd"> Args:</span>
<span class="sd"> action: The action to take</span>
<span class="sd"> Returns:</span>
<span class="sd"> The environment&#39;s step using the action with the next observation containing the timestep info</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="bp">self</span><span class="o">.</span><span class="n">timesteps</span> <span class="o">+=</span> <span class="mi">1</span>
<span class="k">return</span> <span class="nb">super</span><span class="p">()</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">def</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">-&gt;</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">&quot;&quot;&quot;Reset the environment setting the time to zero.</span>
<span class="sd"> Args:</span>
<span class="sd"> seed: The seed to reset the environment</span>
<span class="sd"> options: The options used to reset the environment</span>
<span class="sd"> Returns:</span>
<span class="sd"> Resets the environment with the initial timestep info added the observation</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="bp">self</span><span class="o">.</span><span class="n">timesteps</span> <span class="o">=</span> <span class="mi">0</span>
<span class="k">return</span> <span class="nb">super</span><span class="p">()</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="FrameStackObservation">
<a class="viewcode-back" href="../../../../api/wrappers/observation_wrappers/#gymnasium.wrappers.FrameStackObservation">[docs]</a>
<span class="k">class</span> <span class="nc">FrameStackObservation</span><span class="p">(</span>
<span class="n">gym</span><span class="o">.</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="n">gym</span><span class="o">.</span><span class="n">utils</span><span class="o">.</span><span class="n">RecordConstructorArgs</span><span class="p">,</span>
<span class="p">):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;Stacks the observations from the last ``N`` time steps in a rolling manner.</span>
<span class="sd"> For example, if the number of stacks is 4, then the returned observation contains</span>
<span class="sd"> the most recent 4 observations. For environment &#39;Pendulum-v1&#39;, the original observation</span>
<span class="sd"> is an array with shape [3], so if we stack 4 observations, the processed observation</span>
<span class="sd"> has shape [4, 3].</span>
<span class="sd"> Users have options for the padded observation used:</span>
<span class="sd"> * &quot;reset&quot; (default) - The reset value is repeated</span>
<span class="sd"> * &quot;zero&quot; - A &quot;zero&quot;-like instance of the observation space</span>
<span class="sd"> * custom - An instance of the observation space</span>
<span class="sd"> No vector version of the wrapper exists.</span>
<span class="sd"> Example:</span>
<span class="sd"> &gt;&gt;&gt; import gymnasium as gym</span>
<span class="sd"> &gt;&gt;&gt; from gymnasium.wrappers import FrameStackObservation</span>
<span class="sd"> &gt;&gt;&gt; env = gym.make(&quot;CarRacing-v2&quot;)</span>
<span class="sd"> &gt;&gt;&gt; env = FrameStackObservation(env, stack_size=4)</span>
<span class="sd"> &gt;&gt;&gt; env.observation_space</span>
<span class="sd"> Box(0, 255, (4, 96, 96, 3), uint8)</span>
<span class="sd"> &gt;&gt;&gt; obs, _ = env.reset()</span>
<span class="sd"> &gt;&gt;&gt; obs.shape</span>
<span class="sd"> (4, 96, 96, 3)</span>
<span class="sd"> Example with different padding observations:</span>
<span class="sd"> &gt;&gt;&gt; env = gym.make(&quot;CartPole-v1&quot;)</span>
<span class="sd"> &gt;&gt;&gt; env.reset(seed=123)</span>
<span class="sd"> (array([ 0.01823519, -0.0446179 , -0.02796401, -0.03156282], dtype=float32), {})</span>
<span class="sd"> &gt;&gt;&gt; stacked_env = FrameStackObservation(env, 3) # the default is padding_type=&quot;reset&quot;</span>
<span class="sd"> &gt;&gt;&gt; stacked_env.reset(seed=123)</span>
<span class="sd"> (array([[ 0.01823519, -0.0446179 , -0.02796401, -0.03156282],</span>
<span class="sd"> [ 0.01823519, -0.0446179 , -0.02796401, -0.03156282],</span>
<span class="sd"> [ 0.01823519, -0.0446179 , -0.02796401, -0.03156282]],</span>
<span class="sd"> dtype=float32), {})</span>
<span class="sd"> &gt;&gt;&gt; stacked_env = FrameStackObservation(env, 3, padding_type=&quot;zero&quot;)</span>
<span class="sd"> &gt;&gt;&gt; stacked_env.reset(seed=123)</span>
<span class="sd"> (array([[ 0. , 0. , 0. , 0. ],</span>
<span class="sd"> [ 0. , 0. , 0. , 0. ],</span>
<span class="sd"> [ 0.01823519, -0.0446179 , -0.02796401, -0.03156282]],</span>
<span class="sd"> dtype=float32), {})</span>
<span class="sd"> &gt;&gt;&gt; stacked_env = FrameStackObservation(env, 3, padding_type=np.array([1, -1, 0, 2], dtype=np.float32))</span>
<span class="sd"> &gt;&gt;&gt; stacked_env.reset(seed=123)</span>
<span class="sd"> (array([[ 1. , -1. , 0. , 2. ],</span>
<span class="sd"> [ 1. , -1. , 0. , 2. ],</span>
<span class="sd"> [ 0.01823519, -0.0446179 , -0.02796401, -0.03156282]],</span>
<span class="sd"> dtype=float32), {})</span>
<span class="sd"> Change logs:</span>
<span class="sd"> * v0.15.0 - Initially add as ``FrameStack`` with support for lz4</span>
<span class="sd"> * v1.0.0 - Rename to ``FrameStackObservation`` and remove lz4 and ``LazyFrame`` support</span>
<span class="sd"> along with adding the ``padding_type`` parameter</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">def</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">gym</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="n">stack_size</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span>
<span class="o">*</span><span class="p">,</span>
<span class="n">padding_type</span><span class="p">:</span> <span class="nb">str</span> <span class="o">|</span> <span class="n">ObsType</span> <span class="o">=</span> <span class="s2">&quot;reset&quot;</span><span class="p">,</span>
<span class="p">):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;Observation wrapper that stacks the observations in a rolling manner.</span>
<span class="sd"> Args:</span>
<span class="sd"> env: The environment to apply the wrapper</span>
<span class="sd"> stack_size: The number of frames to stack.</span>
<span class="sd"> padding_type: The padding type to use when stacking the observations, options: &quot;reset&quot;, &quot;zero&quot;, custom obs</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">gym</span><span class="o">.</span><span class="n">utils</span><span class="o">.</span><span class="n">RecordConstructorArgs</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">stack_size</span><span class="o">=</span><span class="n">stack_size</span><span class="p">,</span> <span class="n">padding_type</span><span class="o">=</span><span class="n">padding_type</span>
<span class="p">)</span>
<span class="n">gym</span><span class="o">.</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">if</span> <span class="ow">not</span> <span class="n">np</span><span class="o">.</span><span class="n">issubdtype</span><span class="p">(</span><span class="nb">type</span><span class="p">(</span><span class="n">stack_size</span><span class="p">),</span> <span class="n">np</span><span class="o">.</span><span class="n">integer</span><span class="p">):</span>
<span class="k">raise</span> <span class="ne">TypeError</span><span class="p">(</span>
<span class="sa">f</span><span class="s2">&quot;The stack_size is expected to be an integer, actual type: </span><span class="si">{</span><span class="nb">type</span><span class="p">(</span><span class="n">stack_size</span><span class="p">)</span><span class="si">}</span><span class="s2">&quot;</span>
<span class="p">)</span>
<span class="k">if</span> <span class="ow">not</span> <span class="mi">1</span> <span class="o">&lt;</span> <span class="n">stack_size</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span>
<span class="sa">f</span><span class="s2">&quot;The stack_size needs to be greater than one, actual value: </span><span class="si">{</span><span class="n">stack_size</span><span class="si">}</span><span class="s2">&quot;</span>
<span class="p">)</span>
<span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">padding_type</span><span class="p">,</span> <span class="nb">str</span><span class="p">)</span> <span class="ow">and</span> <span class="p">(</span>
<span class="n">padding_type</span> <span class="o">==</span> <span class="s2">&quot;reset&quot;</span> <span class="ow">or</span> <span class="n">padding_type</span> <span class="o">==</span> <span class="s2">&quot;zero&quot;</span>
<span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">padding_value</span><span class="p">:</span> <span class="n">ObsType</span> <span class="o">=</span> <span class="n">create_zero_array</span><span class="p">(</span><span class="n">env</span><span class="o">.</span><span class="n">observation_space</span><span class="p">)</span>
<span class="k">elif</span> <span class="n">padding_type</span> <span class="ow">in</span> <span class="n">env</span><span class="o">.</span><span class="n">observation_space</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">padding_value</span> <span class="o">=</span> <span class="n">padding_type</span>
<span class="n">padding_type</span> <span class="o">=</span> <span class="s2">&quot;_custom&quot;</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">padding_type</span><span class="p">,</span> <span class="nb">str</span><span class="p">):</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span> <span class="c1"># we are guessing that the user just entered the &quot;reset&quot; or &quot;zero&quot; wrong</span>
<span class="sa">f</span><span class="s2">&quot;Unexpected `padding_type`, expected &#39;reset&#39;, &#39;zero&#39; or a custom observation space, actual value: </span><span class="si">{</span><span class="n">padding_type</span><span class="si">!r}</span><span class="s2">&quot;</span>
<span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span>
<span class="sa">f</span><span class="s2">&quot;Unexpected `padding_type`, expected &#39;reset&#39;, &#39;zero&#39; or a custom observation space, actual value: </span><span class="si">{</span><span class="n">padding_type</span><span class="si">!r}</span><span class="s2"> not an instance of env observation (</span><span class="si">{</span><span class="n">env</span><span class="o">.</span><span class="n">observation_space</span><span class="si">}</span><span class="s2">)&quot;</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">batch_space</span><span class="p">(</span><span class="n">env</span><span class="o">.</span><span class="n">observation_space</span><span class="p">,</span> <span class="n">n</span><span class="o">=</span><span class="n">stack_size</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">stack_size</span><span class="p">:</span> <span class="n">Final</span><span class="p">[</span><span class="nb">int</span><span class="p">]</span> <span class="o">=</span> <span class="n">stack_size</span>
<span class="bp">self</span><span class="o">.</span><span class="n">padding_type</span><span class="p">:</span> <span class="n">Final</span><span class="p">[</span><span class="nb">str</span><span class="p">]</span> <span class="o">=</span> <span class="n">padding_type</span>
<span class="bp">self</span><span class="o">.</span><span class="n">obs_queue</span> <span class="o">=</span> <span class="n">deque</span><span class="p">(</span>
<span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">padding_value</span> <span class="k">for</span> <span class="n">_</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">stack_size</span><span class="p">)],</span> <span class="n">maxlen</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">stack_size</span>
<span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">stacked_obs</span> <span class="o">=</span> <span class="n">create_empty_array</span><span class="p">(</span><span class="n">env</span><span class="o">.</span><span class="n">observation_space</span><span class="p">,</span> <span class="n">n</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">stack_size</span><span class="p">)</span>
<span class="k">def</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">-&gt;</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">&quot;&quot;&quot;Steps through the environment, appending the observation to the frame buffer.</span>
<span class="sd"> Args:</span>
<span class="sd"> action: The action to step through the environment with</span>
<span class="sd"> Returns:</span>
<span class="sd"> Stacked observations, reward, terminated, truncated, and info from the environment</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">obs</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="bp">self</span><span class="o">.</span><span class="n">obs_queue</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">obs</span><span class="p">)</span>
<span class="n">updated_obs</span> <span class="o">=</span> <span class="n">deepcopy</span><span class="p">(</span>
<span class="n">concatenate</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">observation_space</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">obs_queue</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">stacked_obs</span><span class="p">)</span>
<span class="p">)</span>
<span class="k">return</span> <span class="n">updated_obs</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="k">def</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">-&gt;</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">&quot;&quot;&quot;Reset the environment, returning the stacked observation and info.</span>
<span class="sd"> Args:</span>
<span class="sd"> seed: The environment seed</span>
<span class="sd"> options: The reset options</span>
<span class="sd"> Returns:</span>
<span class="sd"> The stacked observations and info</span>
<span class="sd"> &quot;&quot;&quot;</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">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">padding_type</span> <span class="o">==</span> <span class="s2">&quot;reset&quot;</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">padding_value</span> <span class="o">=</span> <span class="n">obs</span>
<span class="k">for</span> <span class="n">_</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">stack_size</span> <span class="o">-</span> <span class="mi">1</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">obs_queue</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">padding_value</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">obs_queue</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">obs</span><span class="p">)</span>
<span class="n">updated_obs</span> <span class="o">=</span> <span class="n">deepcopy</span><span class="p">(</span>
<span class="n">concatenate</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">observation_space</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">obs_queue</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">stacked_obs</span><span class="p">)</span>
<span class="p">)</span>
<span class="k">return</span> <span class="n">updated_obs</span><span class="p">,</span> <span class="n">info</span></div>
<div class="viewcode-block" id="NormalizeObservation">
<a class="viewcode-back" href="../../../../api/wrappers/observation_wrappers/#gymnasium.wrappers.NormalizeObservation">[docs]</a>
<span class="k">class</span> <span class="nc">NormalizeObservation</span><span class="p">(</span>
<span class="n">gym</span><span class="o">.</span><span class="n">ObservationWrapper</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">gym</span><span class="o">.</span><span class="n">utils</span><span class="o">.</span><span class="n">RecordConstructorArgs</span><span class="p">,</span>
<span class="p">):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;Normalizes observations to be centered at the mean with unit variance.</span>
<span class="sd"> The property :attr:`update_running_mean` allows to freeze/continue the running mean calculation of the observation</span>
<span class="sd"> statistics. If ``True`` (default), the ``RunningMeanStd`` will get updated every time ``step`` or ``reset`` is called.</span>
<span class="sd"> If ``False``, the calculated statistics are used but not updated anymore; this may be used during evaluation.</span>
<span class="sd"> A vector version of the wrapper exists :class:`gymnasium.wrappers.vector.NormalizeObservation`.</span>
<span class="sd"> Note:</span>
<span class="sd"> The normalization depends on past trajectories and observations will not be normalized correctly if the wrapper was</span>
<span class="sd"> newly instantiated or the policy was changed recently.</span>
<span class="sd"> Example:</span>
<span class="sd"> &gt;&gt;&gt; import numpy as np</span>
<span class="sd"> &gt;&gt;&gt; import gymnasium as gym</span>
<span class="sd"> &gt;&gt;&gt; env = gym.make(&quot;CartPole-v1&quot;)</span>
<span class="sd"> &gt;&gt;&gt; obs, info = env.reset(seed=123)</span>
<span class="sd"> &gt;&gt;&gt; term, trunc = False, False</span>
<span class="sd"> &gt;&gt;&gt; while not (term or trunc):</span>
<span class="sd"> ... obs, _, term, trunc, _ = env.step(1)</span>
<span class="sd"> ...</span>
<span class="sd"> &gt;&gt;&gt; obs</span>
<span class="sd"> array([ 0.1511158 , 1.7183299 , -0.25533703, -2.8914354 ], dtype=float32)</span>
<span class="sd"> &gt;&gt;&gt; env = gym.make(&quot;CartPole-v1&quot;)</span>
<span class="sd"> &gt;&gt;&gt; env = NormalizeObservation(env)</span>
<span class="sd"> &gt;&gt;&gt; obs, info = env.reset(seed=123)</span>
<span class="sd"> &gt;&gt;&gt; term, trunc = False, False</span>
<span class="sd"> &gt;&gt;&gt; while not (term or trunc):</span>
<span class="sd"> ... obs, _, term, trunc, _ = env.step(1)</span>
<span class="sd"> &gt;&gt;&gt; obs</span>
<span class="sd"> array([ 2.0059888, 1.5676788, -1.9944268, -1.6120394], dtype=float32)</span>
<span class="sd"> Change logs:</span>
<span class="sd"> * v0.21.0 - Initially add</span>
<span class="sd"> * v1.0.0 - Add `update_running_mean` attribute to allow disabling of updating the running mean / standard, particularly useful for evaluation time.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">def</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">gym</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="n">epsilon</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">1e-8</span><span class="p">):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;This wrapper will normalize observations such that each observation is centered with unit variance.</span>
<span class="sd"> Args:</span>
<span class="sd"> env (Env): The environment to apply the wrapper</span>
<span class="sd"> epsilon: A stability parameter that is used when scaling the observations.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">gym</span><span class="o">.</span><span class="n">utils</span><span class="o">.</span><span class="n">RecordConstructorArgs</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">epsilon</span><span class="o">=</span><span class="n">epsilon</span><span class="p">)</span>
<span class="n">gym</span><span class="o">.</span><span class="n">ObservationWrapper</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="bp">self</span><span class="o">.</span><span class="n">obs_rms</span> <span class="o">=</span> <span class="n">RunningMeanStd</span><span class="p">(</span>
<span class="n">shape</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">observation_space</span><span class="o">.</span><span class="n">shape</span><span class="p">,</span> <span class="n">dtype</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">observation_space</span><span class="o">.</span><span class="n">dtype</span>
<span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">epsilon</span> <span class="o">=</span> <span class="n">epsilon</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_update_running_mean</span> <span class="o">=</span> <span class="kc">True</span>
<span class="nd">@property</span>
<span class="k">def</span> <span class="nf">update_running_mean</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="nb">bool</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;Property to freeze/continue the running mean calculation of the observation statistics.&quot;&quot;&quot;</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_update_running_mean</span>
<span class="nd">@update_running_mean</span><span class="o">.</span><span class="n">setter</span>
<span class="k">def</span> <span class="nf">update_running_mean</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">setting</span><span class="p">:</span> <span class="nb">bool</span><span class="p">):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;Sets the property to freeze/continue the running mean calculation of the observation statistics.&quot;&quot;&quot;</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_update_running_mean</span> <span class="o">=</span> <span class="n">setting</span>
<span class="k">def</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">-&gt;</span> <span class="n">WrapperObsType</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;Normalises the observation using the running mean and variance of the observations.&quot;&quot;&quot;</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_update_running_mean</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">obs_rms</span><span class="o">.</span><span class="n">update</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">([</span><span class="n">observation</span><span class="p">]))</span>
<span class="k">return</span> <span class="p">(</span><span class="n">observation</span> <span class="o">-</span> <span class="bp">self</span><span class="o">.</span><span class="n">obs_rms</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span> <span class="o">/</span> <span class="n">np</span><span class="o">.</span><span class="n">sqrt</span><span class="p">(</span>
<span class="bp">self</span><span class="o">.</span><span class="n">obs_rms</span><span class="o">.</span><span class="n">var</span> <span class="o">+</span> <span class="bp">self</span><span class="o">.</span><span class="n">epsilon</span>
<span class="p">)</span></div>
<div class="viewcode-block" id="MaxAndSkipObservation">
<a class="viewcode-back" href="../../../../api/wrappers/observation_wrappers/#gymnasium.wrappers.MaxAndSkipObservation">[docs]</a>
<span class="k">class</span> <span class="nc">MaxAndSkipObservation</span><span class="p">(</span>
<span class="n">gym</span><span class="o">.</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="n">gym</span><span class="o">.</span><span class="n">utils</span><span class="o">.</span><span class="n">RecordConstructorArgs</span><span class="p">,</span>
<span class="p">):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;Skips the N-th frame (observation) and return the max values between the two last observations.</span>
<span class="sd"> No vector version of the wrapper exists.</span>
<span class="sd"> Note:</span>
<span class="sd"> This wrapper is based on the wrapper from [stable-baselines3](https://stable-baselines3.readthedocs.io/en/master/_modules/stable_baselines3/common/atari_wrappers.html#MaxAndSkipEnv)</span>
<span class="sd"> Example:</span>
<span class="sd"> &gt;&gt;&gt; import gymnasium as gym</span>
<span class="sd"> &gt;&gt;&gt; env = gym.make(&quot;CartPole-v1&quot;)</span>
<span class="sd"> &gt;&gt;&gt; obs0, *_ = env.reset(seed=123)</span>
<span class="sd"> &gt;&gt;&gt; obs1, *_ = env.step(1)</span>
<span class="sd"> &gt;&gt;&gt; obs2, *_ = env.step(1)</span>
<span class="sd"> &gt;&gt;&gt; obs3, *_ = env.step(1)</span>
<span class="sd"> &gt;&gt;&gt; obs4, *_ = env.step(1)</span>
<span class="sd"> &gt;&gt;&gt; skip_and_max_obs = np.max(np.stack([obs3, obs4], axis=0), axis=0)</span>
<span class="sd"> &gt;&gt;&gt; env = gym.make(&quot;CartPole-v1&quot;)</span>
<span class="sd"> &gt;&gt;&gt; wrapped_env = MaxAndSkipObservation(env)</span>
<span class="sd"> &gt;&gt;&gt; wrapped_obs0, *_ = wrapped_env.reset(seed=123)</span>
<span class="sd"> &gt;&gt;&gt; wrapped_obs1, *_ = wrapped_env.step(1)</span>
<span class="sd"> &gt;&gt;&gt; np.all(obs0 == wrapped_obs0)</span>
<span class="sd"> True</span>
<span class="sd"> &gt;&gt;&gt; np.all(wrapped_obs1 == skip_and_max_obs)</span>
<span class="sd"> True</span>
<span class="sd"> Change logs:</span>
<span class="sd"> * v1.0.0 - Initially add</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">def</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">gym</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="n">skip</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">4</span><span class="p">):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;This wrapper will return only every ``skip``-th frame (frameskipping) and return the max between the two last frames.</span>
<span class="sd"> Args:</span>
<span class="sd"> env (Env): The environment to apply the wrapper</span>
<span class="sd"> skip: The number of frames to skip</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">gym</span><span class="o">.</span><span class="n">utils</span><span class="o">.</span><span class="n">RecordConstructorArgs</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">skip</span><span class="o">=</span><span class="n">skip</span><span class="p">)</span>
<span class="n">gym</span><span class="o">.</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">if</span> <span class="ow">not</span> <span class="n">np</span><span class="o">.</span><span class="n">issubdtype</span><span class="p">(</span><span class="nb">type</span><span class="p">(</span><span class="n">skip</span><span class="p">),</span> <span class="n">np</span><span class="o">.</span><span class="n">integer</span><span class="p">):</span>
<span class="k">raise</span> <span class="ne">TypeError</span><span class="p">(</span>
<span class="sa">f</span><span class="s2">&quot;The skip is expected to be an integer, actual type: </span><span class="si">{</span><span class="nb">type</span><span class="p">(</span><span class="n">skip</span><span class="p">)</span><span class="si">}</span><span class="s2">&quot;</span>
<span class="p">)</span>
<span class="k">if</span> <span class="n">skip</span> <span class="o">&lt;</span> <span class="mi">2</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span>
<span class="sa">f</span><span class="s2">&quot;The skip value needs to be equal or greater than two, actual value: </span><span class="si">{</span><span class="n">skip</span><span class="si">}</span><span class="s2">&quot;</span>
<span class="p">)</span>
<span class="k">if</span> <span class="n">env</span><span class="o">.</span><span class="n">observation_space</span><span class="o">.</span><span class="n">shape</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s2">&quot;The observation space must have the shape attribute.&quot;</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_skip</span> <span class="o">=</span> <span class="n">skip</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_obs_buffer</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">zeros</span><span class="p">(</span>
<span class="p">(</span><span class="mi">2</span><span class="p">,</span> <span class="o">*</span><span class="n">env</span><span class="o">.</span><span class="n">observation_space</span><span class="o">.</span><span class="n">shape</span><span class="p">),</span> <span class="n">dtype</span><span class="o">=</span><span class="n">env</span><span class="o">.</span><span class="n">observation_space</span><span class="o">.</span><span class="n">dtype</span>
<span class="p">)</span>
<span class="k">def</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">-&gt;</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">&quot;&quot;&quot;Step the environment with the given action for ``skip`` steps.</span>
<span class="sd"> Repeat action, sum reward, and max over last observations.</span>
<span class="sd"> Args:</span>
<span class="sd"> action: The action to step through the environment with</span>
<span class="sd"> Returns:</span>
<span class="sd"> Max of the last two observations, reward, terminated, truncated, and info from the environment</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">total_reward</span> <span class="o">=</span> <span class="mf">0.0</span>
<span class="n">terminated</span> <span class="o">=</span> <span class="n">truncated</span> <span class="o">=</span> <span class="kc">False</span>
<span class="n">info</span> <span class="o">=</span> <span class="p">{}</span>
<span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_skip</span><span class="p">):</span>
<span class="n">obs</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">if</span> <span class="n">i</span> <span class="o">==</span> <span class="bp">self</span><span class="o">.</span><span class="n">_skip</span> <span class="o">-</span> <span class="mi">2</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_obs_buffer</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="o">=</span> <span class="n">obs</span>
<span class="k">if</span> <span class="n">i</span> <span class="o">==</span> <span class="bp">self</span><span class="o">.</span><span class="n">_skip</span> <span class="o">-</span> <span class="mi">1</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_obs_buffer</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span> <span class="o">=</span> <span class="n">obs</span>
<span class="n">total_reward</span> <span class="o">+=</span> <span class="nb">float</span><span class="p">(</span><span class="n">reward</span><span class="p">)</span>
<span class="k">if</span> <span class="n">terminated</span> <span class="ow">or</span> <span class="n">truncated</span><span class="p">:</span>
<span class="k">break</span>
<span class="n">max_frame</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">max</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_obs_buffer</span><span class="p">,</span> <span class="n">axis</span><span class="o">=</span><span class="mi">0</span><span class="p">)</span>
<span class="k">return</span> <span class="n">max_frame</span><span class="p">,</span> <span class="n">total_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>
</pre></div>
</article>
</div>
<footer>
<div class="related-pages">
</div>
<div class="bottom-of-page">
<div class="left-details">
<div class="copyright">
Copyright &#169; 2023 Farama Foundation
</div>
<!--
Made with <a href="https://www.sphinx-doc.org/">Sphinx</a> and <a class="muted-link" href="https://pradyunsg.me">@pradyunsg</a>'s
<a href="https://github.com/pradyunsg/furo">Furo</a>
-->
</div>
<div class="right-details">
<div class="icons">
<a class="muted-link" href="https://github.com/Farama-Foundation/Gymnasium/"
aria-label="On GitHub">
<svg stroke="currentColor" fill="currentColor" stroke-width="0" viewBox="0 0 16 16">
<path fill-rule="evenodd"
d="M8 0C3.58 0 0 3.58 0 8c0 3.54 2.29 6.53 5.47 7.59.4.07.55-.17.55-.38 0-.19-.01-.82-.01-1.49-2.01.37-2.53-.49-2.69-.94-.09-.23-.48-.94-.82-1.13-.28-.15-.68-.52-.01-.53.63-.01 1.08.58 1.23.82.72 1.21 1.87.87 2.33.66.07-.52.28-.87.51-1.07-1.78-.2-3.64-.89-3.64-3.95 0-.87.31-1.59.82-2.15-.08-.2-.36-1.02.08-2.12 0 0 .67-.21 2.2.82.64-.18 1.32-.27 2-.27.68 0 1.36.09 2 .27 1.53-1.04 2.2-.82 2.2-.82.44 1.1.16 1.92.08 2.12.51.56.82 1.27.82 2.15 0 3.07-1.87 3.75-3.65 3.95.29.25.54.73.54 1.48 0 1.07-.01 1.93-.01 2.2 0 .21.15.46.55.38A8.013 8.013 0 0 0 16 8c0-4.42-3.58-8-8-8z">
</path>
</svg>
</a>
</div>
</div>
</div>
</footer>
</div>
<aside class="toc-drawer 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=ed34540e"></script>
<script src="../../../../_static/doctools.js?v=888ff710"></script>
<script src="../../../../_static/sphinx_highlight.js?v=dc90522c"></script>
<script src="../../../../_static/scripts/furo.js?v=7660844c"></script>
<script>
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>