deep-rl-course/pr_587/en/unit8/introduction.html

<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;Introduction&quot;,&quot;local&quot;:&quot;introduction&quot;,&quot;sections&quot;:[],&quot;depth&quot;:1}">
		<link href="/docs/deep-rl-course/pr_587/en/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload">
		<link rel="modulepreload" href="/docs/deep-rl-course/pr_587/en/_app/immutable/entry/start.7c4c7929.js">
		<link rel="modulepreload" href="/docs/deep-rl-course/pr_587/en/_app/immutable/chunks/scheduler.37c15a92.js">
		<link rel="modulepreload" href="/docs/deep-rl-course/pr_587/en/_app/immutable/chunks/singletons.945d9b5d.js">
		<link rel="modulepreload" href="/docs/deep-rl-course/pr_587/en/_app/immutable/chunks/index.18351ede.js">
		<link rel="modulepreload" href="/docs/deep-rl-course/pr_587/en/_app/immutable/chunks/paths.9ffa1e06.js">
		<link rel="modulepreload" href="/docs/deep-rl-course/pr_587/en/_app/immutable/entry/app.d2a43a08.js">
		<link rel="modulepreload" href="/docs/deep-rl-course/pr_587/en/_app/immutable/chunks/index.7cb9c9b8.js">
		<link rel="modulepreload" href="/docs/deep-rl-course/pr_587/en/_app/immutable/nodes/0.e67798fa.js">
		<link rel="modulepreload" href="/docs/deep-rl-course/pr_587/en/_app/immutable/chunks/each.e59479a4.js">
		<link rel="modulepreload" href="/docs/deep-rl-course/pr_587/en/_app/immutable/nodes/85.bedaf615.js">
		<link rel="modulepreload" href="/docs/deep-rl-course/pr_587/en/_app/immutable/chunks/EditOnGithub.858acfec.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;Introduction&quot;,&quot;local&quot;:&quot;introduction&quot;,&quot;sections&quot;:[],&quot;depth&quot;:1}"><!-- HEAD_svelte-u9bgzb_END -->      <p></p>  <h1 class="relative group"><a id="introduction" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#introduction"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>Introduction</span></h1> <img src="https://huggingface.co/datasets/huggingface-deep-rl-course/course-images/resolve/main/en/unit9/thumbnail.png" alt="Unit 8"> <p data-svelte-h="svelte-1028gae">In Unit 6, we learned about Advantage Actor Critic (A2C), a hybrid architecture combining value-based and policy-based methods that helps to stabilize the training by reducing the variance with:</p> <ul data-svelte-h="svelte-1esiva3"><li><em>An Actor</em> that controls <strong>how our agent behaves</strong> (policy-based method).</li> <li><em>A Critic</em> that measures <strong>how good the action taken is</strong> (value-based method).</li></ul> <p>Today we’ll learn about Proximal Policy Optimization (PPO), an architecture that <strong data-svelte-h="svelte-20y8ah">improves our agent’s training stability by avoiding policy updates that are too large</strong>. To do that, we use a ratio that indicates the difference between our current and old policy and clip this ratio to a specific range<!-- HTML_TAG_START --><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mo stretchy="false">[</mo><mn>1</mn><mo>−</mo><mi>ϵ</mi><mo separator="true">,</mo><mn>1</mn><mo>+</mo><mi>ϵ</mi><mo stretchy="false">]</mo></mrow><annotation encoding="application/x-tex"> [1 - \epsilon, 1 + \epsilon] </annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mopen">[</span><span class="mord">1</span><span class="mspace" style="margin-right:0.2222em;"></span><span class="mbin">−</span><span class="mspace" style="margin-right:0.2222em;"></span></span><span class="base"><span class="strut" style="height:0.8389em;vertical-align:-0.1944em;"></span><span class="mord mathnormal">ϵ</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord">1</span><span class="mspace" style="margin-right:0.2222em;"></span><span class="mbin">+</span><span class="mspace" style="margin-right:0.2222em;"></span></span><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mord mathnormal">ϵ</span><span class="mclose">]</span></span></span></span><!-- HTML_TAG_END --> .</p> <p data-svelte-h="svelte-1tdswvm">Doing this will ensure <strong>that our policy update will not be too large and that the training is more stable.</strong></p> <p data-svelte-h="svelte-6tzgaz">This Unit is in two parts:</p> <ul data-svelte-h="svelte-ktbxxa"><li>In this first part, you’ll learn the theory behind PPO and code your PPO agent from scratch using the <a href="https://github.com/vwxyzjn/cleanrl" rel="nofollow">CleanRL</a> implementation. To test its robustness you’ll use LunarLander-v2. LunarLander-v2 <strong>is the first environment you used when you started this course</strong>. At that time, you didn’t know how PPO worked, and now, <strong>you can code it from scratch and train it. How incredible is that 🤩</strong>.</li> <li>In the second part, we’ll get deeper into PPO optimization by using <a href="https://samplefactory.dev/" rel="nofollow">Sample-Factory</a> and train an agent playing vizdoom (an open source version of Doom).</li></ul> <figure data-svelte-h="svelte-87htwd"><img src="https://huggingface.co/datasets/huggingface-deep-rl-course/course-images/resolve/main/en/unit10/environments.png" alt="Environment"> <figcaption>These are the environments you&#39;re going to use to train your agents: VizDoom environments</figcaption></figure> <p data-svelte-h="svelte-1i7vabt">Sound exciting? Let’s get started! 🚀</p> <a class="!text-gray-400 !no-underline text-sm flex items-center not-prose mt-4" href="https://github.com/huggingface/deep-rl-class/blob/main/units/en/unit8/introduction.mdx" target="_blank"><span data-svelte-h="svelte-1kd6by1">&lt;</span> <span data-svelte-h="svelte-x0xyl0">&gt;</span> <span data-svelte-h="svelte-1dajgef"><span class="underline ml-1.5">Update</span> on GitHub</span></a>  <p></p> 
			
			<script>
				{
					__sveltekit_18oo4fq = {
						assets: "/docs/deep-rl-course/pr_587/en",
						base: "/docs/deep-rl-course/pr_587/en",
						env: {}
					};

					const element = document.currentScript.parentElement;

					const data = [null,null];

					Promise.all([
						import("/docs/deep-rl-course/pr_587/en/_app/immutable/entry/start.7c4c7929.js"),
						import("/docs/deep-rl-course/pr_587/en/_app/immutable/entry/app.d2a43a08.js")
					]).then(([kit, app]) => {
						kit.start(app, element, {
							node_ids: [0, 85],
							data,
							form: null,
							error: null
						});
					});
				}
			</script>