deep-rl-course/pr_592/en/unit2/introduction.html

<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;Introduction to Q-Learning&quot;,&quot;local&quot;:&quot;introduction-q-learning&quot;,&quot;sections&quot;:[],&quot;depth&quot;:1}">
		<link href="/docs/deep-rl-course/pr_592/en/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload">
		<link rel="modulepreload" href="/docs/deep-rl-course/pr_592/en/_app/immutable/entry/start.f0057f74.js">
		<link rel="modulepreload" href="/docs/deep-rl-course/pr_592/en/_app/immutable/chunks/scheduler.37c15a92.js">
		<link rel="modulepreload" href="/docs/deep-rl-course/pr_592/en/_app/immutable/chunks/singletons.8a49a196.js">
		<link rel="modulepreload" href="/docs/deep-rl-course/pr_592/en/_app/immutable/chunks/index.18351ede.js">
		<link rel="modulepreload" href="/docs/deep-rl-course/pr_592/en/_app/immutable/chunks/paths.7343a278.js">
		<link rel="modulepreload" href="/docs/deep-rl-course/pr_592/en/_app/immutable/entry/app.596d7feb.js">
		<link rel="modulepreload" href="/docs/deep-rl-course/pr_592/en/_app/immutable/chunks/index.7cb9c9b8.js">
		<link rel="modulepreload" href="/docs/deep-rl-course/pr_592/en/_app/immutable/nodes/0.ce5f0bd8.js">
		<link rel="modulepreload" href="/docs/deep-rl-course/pr_592/en/_app/immutable/chunks/each.e59479a4.js">
		<link rel="modulepreload" href="/docs/deep-rl-course/pr_592/en/_app/immutable/nodes/26.9fd4c6e1.js">
		<link rel="modulepreload" href="/docs/deep-rl-course/pr_592/en/_app/immutable/chunks/EditOnGithub.858acfec.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;Introduction to Q-Learning&quot;,&quot;local&quot;:&quot;introduction-q-learning&quot;,&quot;sections&quot;:[],&quot;depth&quot;:1}"><!-- HEAD_svelte-u9bgzb_END -->      <p></p>  <h1 class="relative group"><a id="introduction-q-learning" 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-q-learning"><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 to Q-Learning</span></h1> <img src="https://huggingface.co/datasets/huggingface-deep-rl-course/course-images/resolve/main/en/unit3/thumbnail.jpg" alt="Unit 2 thumbnail" width="100%"> <p data-svelte-h="svelte-1ynp68f">In the first unit of this class, we learned about Reinforcement Learning (RL), the RL process, and the different methods to solve an RL problem. We also <strong>trained our first agents and uploaded them to the Hugging Face Hub.</strong></p> <p data-svelte-h="svelte-1dfcpck">In this unit, we’re going to <strong>dive deeper into one of the Reinforcement Learning methods: value-based methods</strong> and study our first RL algorithm: <strong>Q-Learning.</strong></p> <p data-svelte-h="svelte-1xt90qk">We’ll also <strong>implement our first RL agent from scratch</strong>, a Q-Learning agent, and will train it in two environments:</p> <ol data-svelte-h="svelte-1avcekp"><li>Frozen-Lake-v1 (non-slippery version): where our agent will need to <strong>go from the starting state (S) to the goal state (G)</strong> by walking only on frozen tiles (F) and avoiding holes (H).</li> <li>An autonomous taxi: where our agent will need <strong>to learn to navigate</strong> a city to <strong>transport its passengers from point A to point B.</strong></li></ol> <img src="https://huggingface.co/datasets/huggingface-deep-rl-course/course-images/resolve/main/en/unit3/envs.gif" alt="Environments"> <p data-svelte-h="svelte-innzr2">Concretely, we will:</p> <ul data-svelte-h="svelte-y97j7m"><li>Learn about <strong>value-based methods</strong>.</li> <li>Learn about the <strong>differences between Monte Carlo and Temporal Difference Learning</strong>.</li> <li>Study and implement <strong>our first RL algorithm</strong>: Q-Learning.</li></ul> <p data-svelte-h="svelte-1c70rr4">This unit is <strong>fundamental if you want to be able to work on Deep Q-Learning</strong>: the first Deep RL algorithm that played Atari games and beat the human level on some of them (breakout, space invaders, etc).</p> <p data-svelte-h="svelte-vkoquy">So 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/unit2/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_mhj5y4 = {
						assets: "/docs/deep-rl-course/pr_592/en",
						base: "/docs/deep-rl-course/pr_592/en",
						env: {}
					};

					const element = document.currentScript.parentElement;

					const data = [null,null];

					Promise.all([
						import("/docs/deep-rl-course/pr_592/en/_app/immutable/entry/start.f0057f74.js"),
						import("/docs/deep-rl-course/pr_592/en/_app/immutable/entry/app.596d7feb.js")
					]).then(([kit, app]) => {
						kit.start(app, element, {
							node_ids: [0, 26],
							data,
							form: null,
							error: null
						});
					});
				}
			</script>