Buckets:

hf-doc-build
/

doc-dev

Files

xet

hf-doc-build/doc-dev / deep-rl-course /pr_587 /en /unit4 /additional-readings.html

rtrm

about 2 months ago

download

raw

9.11 kB

	<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{"title":"Additional Readings","local":"additional-readings","sections":[{"title":"Introduction to Policy Optimization","local":"introduction-to-policy-optimization","sections":[],"depth":2},{"title":"Policy Gradient","local":"policy-gradient","sections":[],"depth":2},{"title":"Implementation","local":"implementation","sections":[],"depth":2}],"depth":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/45.451392d3.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="{"title":"Additional Readings","local":"additional-readings","sections":[{"title":"Introduction to Policy Optimization","local":"introduction-to-policy-optimization","sections":[],"depth":2},{"title":"Policy Gradient","local":"policy-gradient","sections":[],"depth":2},{"title":"Implementation","local":"implementation","sections":[],"depth":2}],"depth":1}"><!-- HEAD_svelte-u9bgzb_END --> <p></p> <h1 class="relative group"><a id="additional-readings" 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="#additional-readings"><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>Additional Readings</span></h1> <p data-svelte-h="svelte-19yxmer">These are <strong>optional readings</strong> if you want to go deeper.</p> <h2 class="relative group"><a id="introduction-to-policy-optimization" 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-to-policy-optimization"><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 Policy Optimization</span></h2> <ul data-svelte-h="svelte-6l3iyx"><li><a href="https://spinningup.openai.com/en/latest/spinningup/rl_intro3.html" rel="nofollow">Part 3: Intro to Policy Optimization - Spinning Up documentation</a></li></ul> <h2 class="relative group"><a id="policy-gradient" 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="#policy-gradient"><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>Policy Gradient</span></h2> <ul data-svelte-h="svelte-11bjwl7"><li><a href="https://johnwlambert.github.io/policy-gradients/" rel="nofollow">https://johnwlambert.github.io/policy-gradients/</a></li> <li><a href="https://jonathan-hui.medium.com/rl-policy-gradients-explained-9b13b688b146" rel="nofollow">RL - Policy Gradient Explained</a></li> <li><a href="http://incompleteideas.net/book/RLbook2020.pdf" rel="nofollow">Chapter 13, Policy Gradient Methods; Reinforcement Learning, an introduction by Richard Sutton and Andrew G. Barto</a></li></ul> <h2 class="relative group"><a id="implementation" 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="#implementation"><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>Implementation</span></h2> <ul data-svelte-h="svelte-lgx1nu"><li><a href="https://github.com/pytorch/examples/blob/main/reinforcement_learning/reinforce.py" rel="nofollow">PyTorch Reinforce implementation</a></li> <li><a href="https://github.com/MrSyee/pg-is-all-you-need" rel="nofollow">Implementations from DDPG to PPO</a></li></ul> <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/unit4/additional-readings.mdx" target="_blank"><span data-svelte-h="svelte-1kd6by1"><</span> <span data-svelte-h="svelte-x0xyl0">></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, 45],
	data,
	form: null,
	error: null
	});
	});
	}
	</script>

Xet Storage Details

Size:: 9.11 kB
Xet hash:: 367ff5f779a67814bd6a549f2fdebcb818d6a8abb175c2f550a7db96c206b0e1

Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.