diffusers/main/en/using-diffusers/rl.html

<meta charset="utf-8" /><meta http-equiv="content-security-policy" content=""><meta name="hf:doc:metadata" content="{&quot;local&quot;:&quot;diffusers.experimental.ValueGuidedRLPipeline&quot;,&quot;title&quot;:&quot;Diffuser Value-guided Planning&quot;}" data-svelte="svelte-1phssyn">
	<link rel="modulepreload" href="/docs/diffusers/main/en/_app/assets/pages/__layout.svelte-hf-doc-builder.css">
	<link rel="modulepreload" href="/docs/diffusers/main/en/_app/start-hf-doc-builder.js">
	<link rel="modulepreload" href="/docs/diffusers/main/en/_app/chunks/vendor-hf-doc-builder.js">
	<link rel="modulepreload" href="/docs/diffusers/main/en/_app/chunks/paths-hf-doc-builder.js">
	<link rel="modulepreload" href="/docs/diffusers/main/en/_app/pages/__layout.svelte-hf-doc-builder.js">
	<link rel="modulepreload" href="/docs/diffusers/main/en/_app/pages/using-diffusers/rl.mdx-hf-doc-builder.js">
	<link rel="modulepreload" href="/docs/diffusers/main/en/_app/chunks/Docstring-hf-doc-builder.js">
	<link rel="modulepreload" href="/docs/diffusers/main/en/_app/chunks/IconCopyLink-hf-doc-builder.js"> 






<h1 class="relative group"><a id="using-diffusers-for-reinforcement-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="#using-diffusers-for-reinforcement-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>Using Diffusers for reinforcement learning
	</span></h1>

<p>Support for one RL model and related pipelines is included in the <code>experimental</code> source of diffusers.
More models and examples coming soon!</p>
<h1 class="relative group"><a id="diffusers.experimental.ValueGuidedRLPipeline" 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="#diffusers.experimental.ValueGuidedRLPipeline"><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>Diffuser Value-guided Planning
	</span></h1>

<p>You can run the model from <a href="https://arxiv.org/abs/2205.09991" rel="nofollow"><em>Planning with Diffusion for Flexible Behavior Synthesis</em></a> with Diffusers.
The script is located in the <a href="https://github.com/huggingface/diffusers/tree/main/examples/rl" rel="nofollow">RL Examples</a> folder.</p>
<p>Or, run this example in Colab <a href="https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/reinforcement_learning_with_diffusers.ipynb" rel="nofollow"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a></p>
<div class="docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8">

<div><span class="group flex space-x-1.5 items-center text-gray-800 bg-gradient-to-r rounded-tr-lg -mt-4 -ml-4 pt-3 px-2.5" id="diffusers.experimental.ValueGuidedRLPipeline"><!-- HTML_TAG_START --><h3 class="!m-0"><span class="flex-1 break-all md:text-lg bg-gradient-to-r px-2.5 py-1.5 rounded-xl from-indigo-50/70 to-white dark:from-gray-900 dark:to-gray-950 dark:text-indigo-300 text-indigo-700"><svg class="mr-1.5 text-indigo-500 inline-block -mt-0.5" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" focusable="false" role="img" width=".8em" height=".8em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 24 24"><path class="uim-quaternary" d="M20.23 7.24L12 12L3.77 7.24a1.98 1.98 0 0 1 .7-.71L11 2.76c.62-.35 1.38-.35 2 0l6.53 3.77c.29.173.531.418.7.71z" opacity=".25" fill="currentColor"></path><path class="uim-tertiary" d="M12 12v9.5a2.09 2.09 0 0 1-.91-.21L4.5 17.48a2.003 2.003 0 0 1-1-1.73v-7.5a2.06 2.06 0 0 1 .27-1.01L12 12z" opacity=".5" fill="currentColor"></path><path class="uim-primary" d="M20.5 8.25v7.5a2.003 2.003 0 0 1-1 1.73l-6.62 3.82c-.275.13-.576.198-.88.2V12l8.23-4.76c.175.308.268.656.27 1.01z" fill="currentColor"></path></svg><span class="font-light">class</span> <span class="font-medium">diffusers.experimental.</span><span class="font-semibold">ValueGuidedRLPipeline</span></span></h3><!-- HTML_TAG_END -->
		<a id="diffusers.experimental.ValueGuidedRLPipeline" class="header-link invisible with-hover:group-hover:visible pr-2" href="#diffusers.experimental.ValueGuidedRLPipeline"><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></a>
		<a class="!ml-auto !text-gray-400 !no-underline text-sm flex items-center" href="https://github.com/huggingface/diffusers/blob/main/src/diffusers/experimental/rl/value_guided_sampling.py#L25" target="_blank"><span>&lt;</span>
				<span class="hidden md:block mx-0.5 hover:!underline">source</span>
				<span>&gt;</span></a></span>
	<p class="font-mono text-xs md:text-sm !leading-relaxed !my-6"><span>(</span>
			<span class="comma cursor-pointer"><span class="rounded hover:bg-black hover:text-white dark:hover:bg-white dark:hover:text-black">value_function<span class="opacity-60">: UNet1DModel</span></span>
				</span><span class="comma cursor-pointer"><span class="rounded hover:bg-black hover:text-white dark:hover:bg-white dark:hover:text-black">unet<span class="opacity-60">: UNet1DModel</span></span>
				</span><span class="comma cursor-pointer"><span class="rounded hover:bg-black hover:text-white dark:hover:bg-white dark:hover:text-black">scheduler<span class="opacity-60">: DDPMScheduler</span></span>
				</span><span class="comma cursor-default"><span class="rounded hover:bg-black hover:text-white dark:hover:bg-white dark:hover:text-black">env<span class="opacity-60"></span></span>
				</span>
			<span>)</span>
			</p>

	
	<div class="!mb-10 relative docstring-details ">
		<p class="flex items-center font-semibold !mt-2 !mb-2 text-gray-800">Parameters <span class="flex-auto border-t-2 border-gray-100 dark:border-gray-700 ml-3"></span></p>
			<ul class="px-2"><li class="text-base !pl-4 my-3 rounded "><span class="group flex space-x-1.5 items-start"><a id="diffusers.experimental.ValueGuidedRLPipeline.value_function" class="header-link block pr-0.5 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="#diffusers.experimental.ValueGuidedRLPipeline.value_function"><span><svg class="text-smd" 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><!-- HTML_TAG_START --><strong>value_function</strong> (<a href="/docs/diffusers/main/en/api/models/unet#diffusers.UNet1DModel">UNet1DModel</a>) &#x2014; A specialized UNet for fine-tuning trajectories base on reward.<!-- HTML_TAG_END -->
							</span></span>
					</li><li class="text-base !pl-4 my-3 rounded "><span class="group flex space-x-1.5 items-start"><a id="diffusers.experimental.ValueGuidedRLPipeline.unet" class="header-link block pr-0.5 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="#diffusers.experimental.ValueGuidedRLPipeline.unet"><span><svg class="text-smd" 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><!-- HTML_TAG_START --><strong>unet</strong> (<a href="/docs/diffusers/main/en/api/models/unet#diffusers.UNet1DModel">UNet1DModel</a>) &#x2014; U-Net architecture to denoise the encoded trajectories.<!-- HTML_TAG_END -->
							</span></span>
					</li><li class="text-base !pl-4 my-3 rounded "><span class="group flex space-x-1.5 items-start"><a id="diffusers.experimental.ValueGuidedRLPipeline.scheduler" class="header-link block pr-0.5 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="#diffusers.experimental.ValueGuidedRLPipeline.scheduler"><span><svg class="text-smd" 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><!-- HTML_TAG_START --><strong>scheduler</strong> (<a href="/docs/diffusers/main/en/api/schedulers/overview#diffusers.SchedulerMixin">SchedulerMixin</a>) &#x2014;
A scheduler to be used in combination with <code>unet</code> to denoise the encoded trajectories. Default for this
application is <a href="/docs/diffusers/main/en/api/schedulers/ddpm#diffusers.DDPMScheduler">DDPMScheduler</a>.
env &#x2014; An environment following the OpenAI gym API to act in. For now only Hopper has pretrained models.<!-- HTML_TAG_END -->
							</span></span>
					</li></ul>
		
		
		</div></div>
<p>This model inherits from <a href="/docs/diffusers/main/en/api/pipelines/overview#diffusers.DiffusionPipeline">DiffusionPipeline</a>. Check the superclass documentation for the generic methods the
library implements for all the pipelines (such as downloading or saving, running on a particular device, etc.)
Pipeline for sampling actions from a diffusion model trained to predict sequences of states.</p>
<p>Original implementation inspired by this repository: <a href="https://github.com/jannerm/diffuser" rel="nofollow">https://github.com/jannerm/diffuser</a>.</p></div>


		<script type="module" data-hydrate="6oidk0">
		import { start } from "/docs/diffusers/main/en/_app/start-hf-doc-builder.js";
		start({
			target: document.querySelector('[data-hydrate="6oidk0"]').parentNode,
			paths: {"base":"/docs/diffusers/main/en","assets":"/docs/diffusers/main/en"},
			session: {},
			route: false,
			spa: false,
			trailing_slash: "never",
			hydrate: {
				status: 200,
				error: null,
				nodes: [
					import("/docs/diffusers/main/en/_app/pages/__layout.svelte-hf-doc-builder.js"),
						import("/docs/diffusers/main/en/_app/pages/using-diffusers/rl.mdx-hf-doc-builder.js")
				],
				params: {}
			}
		});
	</script>