openenv/pr_749/en/tutorials/index.html

<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;Tutorials&quot;,&quot;local&quot;:&quot;tutorials&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;New to OpenEnv? Start Here&quot;,&quot;local&quot;:&quot;new-to-openenv-start-here&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Topic Tutorials&quot;,&quot;local&quot;:&quot;topic-tutorials&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2}],&quot;depth&quot;:1}">
		<link href="/docs/openenv/pr_749/en/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload">
		<link rel="modulepreload" href="/docs/openenv/pr_749/en/_app/immutable/entry/start.85477f45.js">
		<link rel="modulepreload" href="/docs/openenv/pr_749/en/_app/immutable/chunks/scheduler.2b22cead.js">
		<link rel="modulepreload" href="/docs/openenv/pr_749/en/_app/immutable/chunks/singletons.63566282.js">
		<link rel="modulepreload" href="/docs/openenv/pr_749/en/_app/immutable/chunks/paths.dd876c7b.js">
		<link rel="modulepreload" href="/docs/openenv/pr_749/en/_app/immutable/entry/app.51835dc5.js">
		<link rel="modulepreload" href="/docs/openenv/pr_749/en/_app/immutable/chunks/preload-helper.0820fbc7.js">
		<link rel="modulepreload" href="/docs/openenv/pr_749/en/_app/immutable/chunks/index.1a0e8013.js">
		<link rel="modulepreload" href="/docs/openenv/pr_749/en/_app/immutable/nodes/0.167255c0.js">
		<link rel="modulepreload" href="/docs/openenv/pr_749/en/_app/immutable/chunks/each.e59479a4.js">
		<link rel="modulepreload" href="/docs/openenv/pr_749/en/_app/immutable/nodes/60.273535c3.js">
		<link rel="modulepreload" href="/docs/openenv/pr_749/en/_app/immutable/chunks/Heading.c0d3f116.js">
		<link rel="modulepreload" href="/docs/openenv/pr_749/en/_app/immutable/chunks/MermaidChart.svelte_svelte_type_style_lang.21bcf336.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;Tutorials&quot;,&quot;local&quot;:&quot;tutorials&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;New to OpenEnv? Start Here&quot;,&quot;local&quot;:&quot;new-to-openenv-start-here&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Topic Tutorials&quot;,&quot;local&quot;:&quot;topic-tutorials&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2}],&quot;depth&quot;:1}"><!-- HEAD_svelte-u9bgzb_END -->      <p></p>  <div class="items-center shrink-0 min-w-[100px] max-sm:min-w-[50px] justify-end ml-auto flex" style="float: right; margin-left: 10px; display: inline-flex; position: relative; z-index: 10;"><div class="inline-flex rounded-md max-sm:rounded-sm"><button class="inline-flex items-center gap-1 h-7 max-sm:h-7 px-2 max-sm:px-1.5 text-sm font-medium text-gray-800 border border-r-0 rounded-l-md max-sm:rounded-l-sm border-gray-200 bg-white hover:shadow-inner dark:border-gray-850 dark:bg-gray-950 dark:text-gray-200 dark:hover:bg-gray-800" aria-live="polite"><span class="inline-flex items-center justify-center rounded-md p-0.5 max-sm:p-0 hover:text-gray-800 dark:hover:text-gray-200"><svg class="sm:size-3.5 size-3" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg></span> <span>Copy page</span></button> <button class="inline-flex items-center justify-center w-6 max-sm:w-5 h-7 max-sm:h-7 disabled:pointer-events-none text-sm text-gray-500 hover:text-gray-700 dark:hover:text-white rounded-r-md max-sm:rounded-r-sm border border-l transition border-gray-200 bg-white hover:shadow-inner dark:border-gray-850 dark:bg-gray-950 dark:text-gray-200 dark:hover:bg-gray-800" aria-haspopup="menu" aria-expanded="false" aria-label="Open copy menu"><svg class="transition-transform text-gray-400 overflow-visible sm:size-3.5 size-3 rotate-0" width="1em" height="1em" viewBox="0 0 12 7" fill="none" xmlns="http://www.w3.org/2000/svg"><path d="M1 1L6 6L11 1" stroke="currentColor"></path></svg></button></div> </div>  <h1 class="relative group"><a id="tutorials" 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="#tutorials"><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>Tutorials</span></h1>  <h2 class="relative group"><a id="new-to-openenv-start-here" 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="#new-to-openenv-start-here"><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>New to OpenEnv? Start Here</span></h2> <p data-svelte-h="svelte-hi2vy3">The Getting Started Series walks you from zero to deploying your own environment in five short parts. No GPU required.</p> <table data-svelte-h="svelte-a9fs9q"><thead><tr><th>Part</th> <th>What it covers</th> <th>Notebook</th></tr></thead> <tbody><tr><td>1 — Introduction &amp; Quick Start</td> <td>What OpenEnv is, why it exists, and your first environment in under 10 minutes</td> <td><a href="https://colab.research.google.com/github/huggingface/OpenEnv/blob/main/examples/openenv_introduction_quickstart.ipynb" rel="nofollow"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a></td></tr> <tr><td>2 — Using Environments</td> <td>Connect to environments, create policies, run evaluations</td> <td><a href="https://colab.research.google.com/github/huggingface/OpenEnv/blob/main/examples/openenv_using_environments.ipynb" rel="nofollow"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a></td></tr> <tr><td>3 — Building Environments</td> <td>Create a custom environment from scratch</td> <td><a href="https://colab.research.google.com/github/huggingface/OpenEnv/blob/main/examples/openenv_building_environments.ipynb" rel="nofollow"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a></td></tr> <tr><td><a href="../getting_started/environment-builder">4 — Packaging &amp; Deploying</a></td> <td>Package with Docker and deploy to Hugging Face</td> <td>—</td></tr> <tr><td><a href="../getting_started/contributing-envs">5 — Contributing to Hugging Face</a></td> <td>Publish, fork, and share environments on the Hub</td> <td>—</td></tr></tbody></table>  <h2 class="relative group"><a id="topic-tutorials" 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="#topic-tutorials"><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>Topic Tutorials</span></h2> <p data-svelte-h="svelte-1fnfi0n">Already familiar with the basics? These tutorials cover specific workflows in depth.</p> <table data-svelte-h="svelte-wh7ai4"><thead><tr><th>Tutorial</th> <th>What it covers</th> <th>GPU</th> <th>Notebook</th></tr></thead> <tbody><tr><td><a href="openenv-tutorial">OpenEnv Tutorial</a></td> <td>Full introduction to OpenEnv: install, connect to a hosted environment, step through an episode, define a reward function, and run a basic training loop.</td> <td>No</td> <td><a href="https://colab.research.google.com/github/huggingface/OpenEnv/blob/main/examples/OpenEnv_Tutorial.ipynb" rel="nofollow"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a></td></tr> <tr><td><a href="end-to-end-walkthrough">End-to-end walkthrough</a></td> <td>The full pipeline: connect to <code>reasoning_gym</code>, wire it into TRL via <code>environment_factory</code>, fine-tune with GRPO, and push the checkpoint to the Hub.</td> <td>Yes</td> <td><a href="https://colab.research.google.com/github/huggingface/OpenEnv/blob/main/examples/end_to_end_walkthrough.ipynb" rel="nofollow"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a></td></tr> <tr><td><a href="mcp-environment">Building and using MCP environments</a></td> <td>Consume and build MCP-backed environments: list and call tools through <code>step()</code>, register Python functions as tools with FastMCP.</td> <td>No</td> <td><a href="https://colab.research.google.com/github/huggingface/OpenEnv/blob/main/examples/mcp_environment.ipynb" rel="nofollow"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a></td></tr> <tr><td><a href="rubrics">Rubrics</a></td> <td>Compose reward functions from reusable pieces using <code>Gate</code>, <code>WeightedSum</code>, <code>LLMJudge</code>, and <code>TrajectoryRubric</code>.</td> <td>No</td> <td><a href="https://colab.research.google.com/github/huggingface/OpenEnv/blob/main/examples/rubrics.ipynb" rel="nofollow"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a></td></tr> <tr><td><a href="wordle-grpo">Wordle GRPO</a></td> <td>Train an agent to play Wordle using GRPO via TRL’s <code>environment_factory</code>.</td> <td>Yes</td> <td><a href="https://colab.research.google.com/github/huggingface/trl/blob/main/examples/notebooks/openenv_wordle_grpo.ipynb" rel="nofollow"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a></td></tr> <tr><td><a href="rl-training-2048">RL Training with 2048</a></td> <td>Train a language model to play 2048 using GRPO. Covers game-state representation and reward shaping.</td> <td>Yes</td> <td>—</td></tr> <tr><td><a href="evaluation-inspect">Evaluating agents with Inspect AI</a></td> <td>Wrap an OpenEnv environment in an Inspect AI <code>Task</code>, run it via <code>InspectAIHarness</code>, and get a structured <code>EvalResult</code>.</td> <td>No</td> <td><a href="https://colab.research.google.com/github/huggingface/OpenEnv/blob/main/examples/evaluation_inspect.ipynb" rel="nofollow"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a></td></tr> <tr><td><a href="browsergym-harness">BrowserGym Harness Rollouts</a></td> <td>Drive BrowserGym through the OpenEnv harness runtime when a trainer needs token sampling, logprobs, and reward assignment inside the training loop.</td> <td>Yes</td> <td>—</td></tr> <tr><td><a href="sft-warmup">Collecting rollouts for supervised training</a></td> <td>Run a teacher model to collect reward-labeled rollouts, filter them, and fine-tune a student with TRL’s <code>SFTTrainer</code> as a warm-start for GRPO.</td> <td>Yes</td> <td><a href="https://colab.research.google.com/github/huggingface/OpenEnv/blob/main/examples/sft_warmup.ipynb" rel="nofollow"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a></td></tr></tbody></table> <a class="!text-gray-400 !no-underline text-sm flex items-center not-prose mt-4" href="https://github.com/huggingface/openenv/blob/main/docs/source/tutorials/index.md" target="_blank"><svg class="mr-1" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M31,16l-7,7l-1.41-1.41L28.17,16l-5.58-5.59L24,9l7,7z"></path><path d="M1,16l7-7l1.41,1.41L3.83,16l5.58,5.59L8,23l-7-7z"></path><path d="M12.419,25.484L17.639,6.552l1.932,0.518L14.351,26.002z"></path></svg> <span data-svelte-h="svelte-zjs2n5"><span class="underline">Update</span> on GitHub</span></a>  <p></p> 
			
			<script>
				{
					__sveltekit_1qwoa43 = {
						assets: "/docs/openenv/pr_749/en",
						base: "/docs/openenv/pr_749/en",
						env: {}
					};

					const element = document.currentScript.parentElement;

					const data = [null,null];

					Promise.all([
						import("/docs/openenv/pr_749/en/_app/immutable/entry/start.85477f45.js"),
						import("/docs/openenv/pr_749/en/_app/immutable/entry/app.51835dc5.js")
					]).then(([kit, app]) => {
						kit.start(app, element, {
							node_ids: [0, 60],
							data,
							form: null,
							error: null
						});
					});
				}
			</script>