gaspersic/Gymnasium
1
0
Fork 0
mirror of https://github.com/Farama-Foundation/Gymnasium.git synced 2025-08-19 21:42:02 +00:00
Code Issues Packages Projects Releases Wiki Activity
Files
34fc9d196199adba037eef833cf8be7a336b51c1
Gymnasium/v0.28.1/tutorials/training_agents/index.html

752 lines
48 KiB
HTML
Raw Normal View History

Deploying to gh-pages from @ Farama-Foundation/Gymnasium@cab0fbb13d8f3c29c098939144fcbb183bede7f2 🚀
2023-03-25 12:03:31 +00:00
<!doctype html>
<html class="no-js" lang="en">
<head><meta charset="utf-8"/>
<meta name="viewport" content="width=device-width,initial-scale=1"/>
<meta name="color-scheme" content="light dark">
<meta name="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/tutorials/training_agents/index.html" /><meta property="og:image" content="https://gymnasium.farama.org/_static/img/gymnasium-github.png" /><meta name="twitter:card" content="summary_large_image"><meta name="generator" content="Docutils 0.19: https://docutils.sourceforge.io/" />
<link rel="index" title="Index" href="../../genindex/" /><link rel="search" title="Search" href="../../search/" /><link rel="next" title="Training using REINFORCE for Mujoco" href="reinforce_invpend_gym_v26/" /><link rel="prev" title="Training A2C with Vector Envs and Domain Randomization" href="../gymnasium_basics/vector_envs_tutorial/" />
<link rel="canonical" href="https://gymnasium.farama.org/tutorials/training_agents/index.html" />
<link rel="shortcut icon" href="../../_static/favicon.png"/><!-- Generated with Sphinx 6.1.3 and Furo 2022.12.07.dev1 -->
<title>Training Agents - Gymnasium Documentation</title>
<link rel="stylesheet" type="text/css" href="../../_static/pygments.css" />
<link rel="stylesheet" type="text/css" href="../../_static/styles/furo.css?digest=721f65a87c37740baa8d605b09db5bec3a2987a8" />
<link rel="stylesheet" type="text/css" href="../../_static/sg_gallery.css" />
<link rel="stylesheet" type="text/css" href="../../_static/sg_gallery-binder.css" />
<link rel="stylesheet" type="text/css" href="../../_static/sg_gallery-dataframe.css" />
<link rel="stylesheet" type="text/css" href="../../_static/sg_gallery-rendered-html.css" />
<link rel="stylesheet" type="text/css" href="../../_static/styles/furo-extensions.css?digest=b0c92cd440df7c18a0306b0433406327ff2c572f" />
<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>
<!-- <svg viewBox="0 0 24 24" viewBox="0 0 24 24" xmlns="http://www.w3.org/2000/svg">
<line x1="0.5" y1="4.5" x2="23.5" y2="4.5" style="fill: none; "></line>
<line x1="0.5" y1="12" x2="14" y2="12" ></line>
<line x1="0.5" y1="19.5" x2="23.5" y2="19.5"></line>
<polyline style="stroke-width: 0px;" points="17 7 22 12 17 17"></polyline>
</svg> -->
<!-- <svg viewBox="0 0 24 24" xmlns="http://www.w3.org/2000/svg" style="width:20px">
<defs></defs>
<rect y="1" width="22" height="22" rx="2" ry="2" style="fill: none;" x="1"></rect>
<line x1="8" y1="1" x2="8" y2="23"></line>
<polyline style="stroke-linecap: round; fill: none; stroke-linejoin: round;" points="13 7 17 12 13 17"></polyline>
</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="../../content/basic_usage/">Basic Usage</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../content/gym_compatibility/">Compatibility with Gym</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../content/migration-guide/">v21 to v26 Migration Guide</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/">Register and Make</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 child pages in navigation</div><i class="icon"><svg><use href="#svg-arrow-right"></use></svg></i></label><ul>
<li class="toctree-l2"><a class="reference internal" href="../../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/spaces/vector_utils/">Spaces Vector Utils</a></li>
</ul>
</li>
<li class="toctree-l1 has-children"><a class="reference internal" href="../../api/wrappers/">Wrappers</a><input class="toctree-checkbox" id="toctree-checkbox-2" name="toctree-checkbox-2" role="switch" type="checkbox"/><label for="toctree-checkbox-2"><div class="visually-hidden">Toggle child pages in navigation</div><i class="icon"><svg><use href="#svg-arrow-right"></use></svg></i></label><ul>
<li class="toctree-l2"><a class="reference internal" href="../../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"><a class="reference internal" href="../../api/vector/">Vector</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../api/utils/">Utils</a></li>
<li class="toctree-l1 has-children"><a class="reference internal" href="../../api/experimental/">Experimental</a><input class="toctree-checkbox" id="toctree-checkbox-3" name="toctree-checkbox-3" role="switch" type="checkbox"/><label for="toctree-checkbox-3"><div class="visually-hidden">Toggle child pages in navigation</div><i class="icon"><svg><use href="#svg-arrow-right"></use></svg></i></label><ul>
<li class="toctree-l2"><a class="reference internal" href="../../api/experimental/functional/">Functional Environment</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../api/experimental/wrappers/">Wrappers</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../api/experimental/vector/">Vectorizing Environment</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../api/experimental/vector_wrappers/">Vector Environment Wrappers</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../api/experimental/vector_utils/">Utility functions for vectorisation</a></li>
</ul>
</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 child pages in navigation</div><i class="icon"><svg><use href="#svg-arrow-right"></use></svg></i></label><ul>
<li class="toctree-l2"><a class="reference internal" href="../../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 child pages in navigation</div><i class="icon"><svg><use href="#svg-arrow-right"></use></svg></i></label><ul>
<li class="toctree-l2"><a class="reference internal" href="../../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 child pages in navigation</div><i class="icon"><svg><use href="#svg-arrow-right"></use></svg></i></label><ul>
<li class="toctree-l2"><a class="reference internal" href="../../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 child pages in navigation</div><i class="icon"><svg><use href="#svg-arrow-right"></use></svg></i></label><ul>
<li class="toctree-l2"><a class="reference internal" href="../../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_standup/">Humanoid Standup</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/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/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/pusher/">Pusher</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 child pages in navigation</div><i class="icon"><svg><use href="#svg-arrow-right"></use></svg></i></label><ul>
<li class="toctree-l2"><a class="reference internal" href="../../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>
<li class="toctree-l1"><a class="reference internal" href="../../environments/third_party_environments/#third-party-environments-using-gym">Third-Party Environments using Gym</a></li>
</ul>
<p class="caption" role="heading"><span class="caption-text">Tutorials</span></p>
<ul class="current">
<li class="toctree-l1 has-children"><a class="reference internal" href="../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 child pages in navigation</div><i class="icon"><svg><use href="#svg-arrow-right"></use></svg></i></label><ul>
<li class="toctree-l2"><a class="reference internal" href="../gymnasium_basics/handling_time_limits/">Handling Time Limits</a></li>
<li class="toctree-l2"><a class="reference internal" href="../gymnasium_basics/implementing_custom_wrappers/">Implementing Custom Wrappers</a></li>
<li class="toctree-l2"><a class="reference internal" href="../gymnasium_basics/environment_creation/">Make your own custom environment</a></li>
<li class="toctree-l2"><a class="reference internal" href="../gymnasium_basics/vector_envs_tutorial/">Training A2C with Vector Envs and Domain Randomization</a></li>
</ul>
</li>
<li class="toctree-l1 current has-children current-page"><a class="current reference internal" href="#">Training Agents</a><input checked="" 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 child pages in navigation</div><i class="icon"><svg><use href="#svg-arrow-right"></use></svg></i></label><ul>
<li class="toctree-l2"><a class="reference internal" href="reinforce_invpend_gym_v26/">Training using REINFORCE for Mujoco</a></li>
<li class="toctree-l2"><a class="reference internal" href="blackjack_tutorial/">Solving Blackjack with Q-Learning</a></li>
<li class="toctree-l2"><a class="reference internal" href="FrozenLake_tuto/">Frozenlake benchmark</a></li>
</ul>
</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">
<section id="training-agents">
<span id="sphx-glr-tutorials-training-agents"></span><h1>Training Agents<a class="headerlink" href="#training-agents" title="Permalink to this heading">#</a></h1>
<div class="sphx-glr-thumbnails"><div class="sphx-glr-thumbcontainer" tooltip="This tutorial serves 2 purposes: 1. To understand how to implement REINFORCE [1] from scratch ..."><img alt="Training using REINFORCE for Mujoco" src="../../_images/sphx_glr_reinforce_invpend_gym_v26_thumb.png" />
<p><a class="reference internal" href="reinforce_invpend_gym_v26/#sphx-glr-tutorials-training-agents-reinforce-invpend-gym-v26-py"><span class="std std-ref">Training using REINFORCE for Mujoco</span></a></p>
<div class="sphx-glr-thumbnail-title">Training using REINFORCE for Mujoco</div>
</div><div class="sphx-glr-thumbcontainer" tooltip="Solving Blackjack with Q-Learning"><img alt="Solving Blackjack with Q-Learning" src="../../_images/sphx_glr_blackjack_tutorial_thumb.png" />
<p><a class="reference internal" href="blackjack_tutorial/#sphx-glr-tutorials-training-agents-blackjack-tutorial-py"><span class="std std-ref">Solving Blackjack with Q-Learning</span></a></p>
<div class="sphx-glr-thumbnail-title">Solving Blackjack with Q-Learning</div>
</div><div class="sphx-glr-thumbcontainer" tooltip="Frozenlake benchmark"><img alt="Frozenlake benchmark" src="../../_images/sphx_glr_FrozenLake_tuto_thumb.png" />
<p><a class="reference internal" href="FrozenLake_tuto/#sphx-glr-tutorials-training-agents-frozenlake-tuto-py"><span class="std std-ref">Frozenlake benchmark</span></a></p>
<div class="sphx-glr-thumbnail-title">Frozenlake benchmark</div>
</div></div><div class="toctree-wrapper compound">
</div>
</section>
</article>
</div>
<footer>
<div class="related-pages">
<a class="next-page" href="reinforce_invpend_gym_v26/">
<div class="page-info">
<div class="context">
<span>Next</span>
</div>
<div class="title">Training using REINFORCE for Mujoco</div>
</div>
<svg class="furo-related-icon">
<use href="#svg-arrow-right"></use>
</svg>
</a>
<a class="prev-page" href="../gymnasium_basics/vector_envs_tutorial/">
<svg class="furo-related-icon">
<use href="#svg-arrow-right"></use>
</svg>
<div class="page-info">
<div class="context">
<span>Previous</span>
</div>
<div class="title">Training A2C with Vector Envs and Domain Randomization</div>
</div>
</a>
</div>
<div class="bottom-of-page">
<div class="left-details">
<div class="copyright">
Copyright &#169; 2022 Farama Foundation
</div>
<!--
Made with <a href="https://www.sphinx-doc.org/">Sphinx</a> and <a class="muted-link" href="https://pradyunsg.me">@pradyunsg</a>'s
<a href="https://github.com/pradyunsg/furo">Furo</a>
-->
</div>
<div class="right-details">
<div class="icons">
</div>
</div>
</div>
</footer>
</div>
<aside class="toc-drawer 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>
(() => {
if (!localStorage.getItem("shownCookieAlert")) {
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. You can disable it by blocking
the JavaScript coming from www.google-analytics.com.`;
containerElem.appendChild(textElem);
const closeBtn = document.createElement("button");
closeBtn.innerHTML = `<?xml version="1.0" ?><svg viewBox="0 0 32 32" xmlns="http://www.w3.org/2000/svg"><defs><style>.cls-1{fill:none;stroke:#000;stroke-linecap:round;stroke-linejoin:round;stroke-width:2px;}</style></defs><title/><g id="cross"><line class="cls-1" x1="7" x2="25" y1="7" y2="25"/><line class="cls-1" x1="7" x2="25" y1="25" y2="7"/></g></svg>`
closeBtn.onclick = () => {
localStorage.setItem("shownCookieAlert", "true");
boxElem.style.display = "none";
}
containerElem.appendChild(closeBtn);
boxElem.appendChild(containerElem);
document.body.appendChild(boxElem);
}
})()
</script>
<script async src="https://www.googletagmanager.com/gtag/js?id=G-6H9C8TWXZ8"></script>
<script>
window.dataLayer = window.dataLayer || [];
function gtag(){dataLayer.push(arguments);}
gtag('js', new Date());
gtag('config', 'G-6H9C8TWXZ8');
</script>
<script data-url_root="../../" id="documentation_options" src="../../_static/documentation_options.js"></script>
<script src="../../_static/doctools.js"></script>
<script src="../../_static/sphinx_highlight.js"></script>
<script src="../../_static/scripts/furo.js"></script>
<script>
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 = {
"Documentation": [],
"Mature Projects": [],
"Incubating Projects": [],
"Foundation": [
{
name: "About",
link: "https://farama.org/about"
},
{
name: "Standards",
link: "https://farama.org/project_standards",
},
{
name: "Donate",
link: "https://farama.org/donations"
}
]
}
Object.keys(jsonResponse).forEach(key => {
projectJson = jsonResponse[key];
if (projectJson.website !== null) {
projectJson.link = projectJson.website;
sections["Documentation"].push(projectJson)
} else if (projectJson.type == "mature") {
projectJson.link = projectJson.github;
sections["Mature Projects"].push(projectJson)
} else {
projectJson.link = projectJson.github;
sections["Incubating Projects"].push(projectJson)
}
})
const menuContainer = document.querySelector(".farama-header-menu__body");
Object.keys(sections).forEach((key, i) => {
projects = sections[key];
const sectionElem = Object.assign(
document.createElement('div'), {
className:'farama-header-menu__section',
style: "padding-left: 24px"
}
)
sectionElem.appendChild(Object.assign(document.createElement('span'),
{
className:'farama-header-menu__section-title' ,
innerText: key
}
))
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 (key !== "Foundation") {
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);
}
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>
Reference in New Issue Copy Permalink