deep-rl-course/pr_587/en/unit6/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/68.5f585304.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/unit8/thumbnail.png" alt="Thumbnail"> <p data-svelte-h="svelte-dvu1gd">In unit 4, we learned about our first Policy-Based algorithm called <strong>Reinforce</strong>.</p> <p data-svelte-h="svelte-z9stkq">In Policy-Based methods, <strong>we aim to optimize the policy directly without using a value function</strong>. More precisely, Reinforce is part of a subclass of <em>Policy-Based Methods</em> called <em>Policy-Gradient methods</em>. This subclass optimizes the policy directly by <strong>estimating the weights of the optimal policy using Gradient Ascent</strong>.</p> <p data-svelte-h="svelte-1p5t49p">We saw that Reinforce worked well. However, because we use Monte-Carlo sampling to estimate return (we use an entire episode to calculate the return), <strong>we have significant variance in policy gradient estimation</strong>.</p> <p data-svelte-h="svelte-spae8s">Remember that the policy gradient estimation is <strong>the direction of the steepest increase in return</strong>. In other words, how to update our policy weights so that actions that lead to good returns have a higher probability of being taken. The Monte Carlo variance, which we will further study in this unit, <strong>leads to slower training since we need a lot of samples to mitigate it</strong>.</p> <p data-svelte-h="svelte-a75o96">So today we’ll study <strong>Actor-Critic methods</strong>, a hybrid architecture combining value-based and Policy-Based methods that helps to stabilize the training by reducing the variance using:</p> <ul data-svelte-h="svelte-1g2297h"><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 taken action is</strong> (Value-Based method)</li></ul> <p data-svelte-h="svelte-54x6jn">We’ll study one of these hybrid methods, Advantage Actor Critic (A2C), <strong>and train our agent using Stable-Baselines3 in robotic environments</strong>. We’ll train:</p> <ul data-svelte-h="svelte-10o7xql"><li>A robotic arm 🦾 to move to the correct position.</li></ul> <p data-svelte-h="svelte-1lrk2z4">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/unit6/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, 68],
							data,
							form: null,
							error: null
						});
					});
				}
			</script>