deep-rl-course/pr_592/en/unit3/introduction.html

<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;Deep Q-Learning&quot;,&quot;local&quot;:&quot;deep-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/43.31376149.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;Deep Q-Learning&quot;,&quot;local&quot;:&quot;deep-q-learning&quot;,&quot;sections&quot;:[],&quot;depth&quot;:1}"><!-- HEAD_svelte-u9bgzb_END -->      <p></p>  <h1 class="relative group"><a id="deep-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="#deep-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>Deep Q-Learning</span></h1> <img src="https://huggingface.co/datasets/huggingface-deep-rl-course/course-images/resolve/main/en/unit4/thumbnail.jpg" alt="Unit 3 thumbnail" width="100%"> <p data-svelte-h="svelte-zk4w0n">In the last unit, we learned our first reinforcement learning algorithm: Q-Learning, <strong>implemented it from scratch</strong>, and trained it in two environments, FrozenLake-v1 ☃️ and Taxi-v3 🚕.</p> <p>We got excellent results with this simple algorithm, but these environments were relatively simple because the <strong data-svelte-h="svelte-1pgaspr">state space was discrete and small</strong> (16 different states for FrozenLake-v1 and 500 for Taxi-v3). For comparison, the state space in Atari games can <strong>contain<!-- HTML_TAG_START --><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mn>1</mn><msup><mn>0</mn><mn>9</mn></msup></mrow><annotation encoding="application/x-tex">10^{9}</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.8141em;"></span><span class="mord">1</span><span class="mord"><span class="mord">0</span><span class="msupsub"><span class="vlist-t"><span class="vlist-r"><span class="vlist" style="height:0.8141em;"><span style="top:-3.063em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mord mtight">9</span></span></span></span></span></span></span></span></span></span></span></span><!-- HTML_TAG_END --> to<!-- HTML_TAG_START --><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mn>1</mn><msup><mn>0</mn><mn>11</mn></msup></mrow><annotation encoding="application/x-tex">10^{11}</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.8141em;"></span><span class="mord">1</span><span class="mord"><span class="mord">0</span><span class="msupsub"><span class="vlist-t"><span class="vlist-r"><span class="vlist" style="height:0.8141em;"><span style="top:-3.063em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mord mtight">11</span></span></span></span></span></span></span></span></span></span></span></span><!-- HTML_TAG_END --> states</strong>.</p> <p data-svelte-h="svelte-1uzwejl">But as we’ll see, producing and updating a <strong>Q-table can become ineffective in large state space environments.</strong></p> <p data-svelte-h="svelte-v9iwbb">So in this unit, <strong>we’ll study our first Deep Reinforcement Learning agent</strong>: Deep Q-Learning. Instead of using a Q-table, Deep Q-Learning uses a Neural Network that takes a state and approximates Q-values for each action based on that state.</p> <p data-svelte-h="svelte-5gpd3h">And <strong>we’ll train it to play Space Invaders and other Atari environments using <a href="https://github.com/DLR-RM/rl-baselines3-zoo" rel="nofollow">RL-Zoo</a></strong>, a training framework for RL using Stable-Baselines that provides scripts for training, evaluating agents, tuning hyperparameters, plotting results, and recording videos.</p> <img src="https://huggingface.co/datasets/huggingface-deep-rl-course/course-images/resolve/main/en/unit4/atari-envs.gif" alt="Environments"> <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/unit3/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, 43],
							data,
							form: null,
							error: null
						});
					});
				}
			</script>