1
Fork 0
This repository has been archived on 2026-08-15. You can view files and clone it, but you cannot make any changes to it's state, such as pushing and creating new issues, pull requests or comments.
2026SEL3-project-Brittle_St.../api/evaluation/index.html
2026-05-19 20:58:23 +00:00

1369 lines
No EOL
27 KiB
HTML

<!doctype html>
<html lang="en" class="no-js">
<head>
<meta charset="utf-8">
<meta name="viewport" content="width=device-width,initial-scale=1">
<link rel="prev" href="../environment/">
<link rel="next" href="../simulation/">
<link rel="icon" href="../../assets/images/favicon.png">
<meta name="generator" content="mkdocs-1.6.1, mkdocs-material-9.7.6">
<title>Checkpoint & Model Evaluation - Brittle Star Project</title>
<link rel="stylesheet" href="../../assets/stylesheets/main.484c7ddc.min.css">
<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>
<link rel="stylesheet" href="https://fonts.googleapis.com/css?family=Roboto:300,300i,400,400i,700,700i%7CRoboto+Mono:400,400i,700,700i&display=fallback">
<style>:root{--md-text-font:"Roboto";--md-code-font:"Roboto Mono"}</style>
<script>__md_scope=new URL("../..",location),__md_hash=e=>[...e].reduce(((e,_)=>(e<<5)-e+_.charCodeAt(0)),0),__md_get=(e,_=localStorage,t=__md_scope)=>JSON.parse(_.getItem(t.pathname+"."+e)),__md_set=(e,_,t=localStorage,a=__md_scope)=>{try{t.setItem(a.pathname+"."+e,JSON.stringify(_))}catch(e){}}</script>
</head>
<body dir="ltr">
<input class="md-toggle" data-md-toggle="drawer" type="checkbox" id="__drawer" autocomplete="off">
<input class="md-toggle" data-md-toggle="search" type="checkbox" id="__search" autocomplete="off">
<label class="md-overlay" for="__drawer"></label>
<div data-md-component="skip">
<a href="#checkpoint-model-evaluation" class="md-skip">
Skip to content
</a>
</div>
<div data-md-component="announce">
</div>
<header class="md-header md-header--shadow" data-md-component="header">
<nav class="md-header__inner md-grid" aria-label="Header">
<a href="../.." title="Brittle Star Project" class="md-header__button md-logo" aria-label="Brittle Star Project" data-md-component="logo">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M12 8a3 3 0 0 0 3-3 3 3 0 0 0-3-3 3 3 0 0 0-3 3 3 3 0 0 0 3 3m0 3.54C9.64 9.35 6.5 8 3 8v11c3.5 0 6.64 1.35 9 3.54 2.36-2.19 5.5-3.54 9-3.54V8c-3.5 0-6.64 1.35-9 3.54"/></svg>
</a>
<label class="md-header__button md-icon" for="__drawer">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M3 6h18v2H3zm0 5h18v2H3zm0 5h18v2H3z"/></svg>
</label>
<div class="md-header__title" data-md-component="header-title">
<div class="md-header__ellipsis">
<div class="md-header__topic">
<span class="md-ellipsis">
Brittle Star Project
</span>
</div>
<div class="md-header__topic" data-md-component="header-topic">
<span class="md-ellipsis">
Checkpoint &amp; Model Evaluation
</span>
</div>
</div>
</div>
<script>var palette=__md_get("__palette");if(palette&&palette.color){if("(prefers-color-scheme)"===palette.color.media){var media=matchMedia("(prefers-color-scheme: light)"),input=document.querySelector(media.matches?"[data-md-color-media='(prefers-color-scheme: light)']":"[data-md-color-media='(prefers-color-scheme: dark)']");palette.color.media=input.getAttribute("data-md-color-media"),palette.color.scheme=input.getAttribute("data-md-color-scheme"),palette.color.primary=input.getAttribute("data-md-color-primary"),palette.color.accent=input.getAttribute("data-md-color-accent")}for(var[key,value]of Object.entries(palette.color))document.body.setAttribute("data-md-color-"+key,value)}</script>
<label class="md-header__button md-icon" for="__search">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M9.5 3A6.5 6.5 0 0 1 16 9.5c0 1.61-.59 3.09-1.56 4.23l.27.27h.79l5 5-1.5 1.5-5-5v-.79l-.27-.27A6.52 6.52 0 0 1 9.5 16 6.5 6.5 0 0 1 3 9.5 6.5 6.5 0 0 1 9.5 3m0 2C7 5 5 7 5 9.5S7 14 9.5 14 14 12 14 9.5 12 5 9.5 5"/></svg>
</label>
<div class="md-search" data-md-component="search" role="dialog">
<label class="md-search__overlay" for="__search"></label>
<div class="md-search__inner" role="search">
<form class="md-search__form" name="search">
<input type="text" class="md-search__input" name="query" aria-label="Search" placeholder="Search" autocapitalize="off" autocorrect="off" autocomplete="off" spellcheck="false" data-md-component="search-query" required>
<label class="md-search__icon md-icon" for="__search">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M9.5 3A6.5 6.5 0 0 1 16 9.5c0 1.61-.59 3.09-1.56 4.23l.27.27h.79l5 5-1.5 1.5-5-5v-.79l-.27-.27A6.52 6.52 0 0 1 9.5 16 6.5 6.5 0 0 1 3 9.5 6.5 6.5 0 0 1 9.5 3m0 2C7 5 5 7 5 9.5S7 14 9.5 14 14 12 14 9.5 12 5 9.5 5"/></svg>
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M20 11v2H8l5.5 5.5-1.42 1.42L4.16 12l7.92-7.92L13.5 5.5 8 11z"/></svg>
</label>
<nav class="md-search__options" aria-label="Search">
<button type="reset" class="md-search__icon md-icon" title="Clear" aria-label="Clear" tabindex="-1">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M19 6.41 17.59 5 12 10.59 6.41 5 5 6.41 10.59 12 5 17.59 6.41 19 12 13.41 17.59 19 19 17.59 13.41 12z"/></svg>
</button>
</nav>
</form>
<div class="md-search__output">
<div class="md-search__scrollwrap" tabindex="0" data-md-scrollfix>
<div class="md-search-result" data-md-component="search-result">
<div class="md-search-result__meta">
Initializing search
</div>
<ol class="md-search-result__list" role="presentation"></ol>
</div>
</div>
</div>
</div>
</div>
</nav>
</header>
<div class="md-container" data-md-component="container">
<main class="md-main" data-md-component="main">
<div class="md-main__inner md-grid">
<div class="md-sidebar md-sidebar--primary" data-md-component="sidebar" data-md-type="navigation" >
<div class="md-sidebar__scrollwrap">
<div class="md-sidebar__inner">
<nav class="md-nav md-nav--primary" aria-label="Navigation" data-md-level="0">
<label class="md-nav__title" for="__drawer">
<a href="../.." title="Brittle Star Project" class="md-nav__button md-logo" aria-label="Brittle Star Project" data-md-component="logo">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M12 8a3 3 0 0 0 3-3 3 3 0 0 0-3-3 3 3 0 0 0-3 3 3 3 0 0 0 3 3m0 3.54C9.64 9.35 6.5 8 3 8v11c3.5 0 6.64 1.35 9 3.54 2.36-2.19 5.5-3.54 9-3.54V8c-3.5 0-6.64 1.35-9 3.54"/></svg>
</a>
Brittle Star Project
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../.." class="md-nav__link">
<span class="md-ellipsis">
Documentation
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../CONTRIBUTING/" class="md-nav__link">
<span class="md-ellipsis">
Contribution Guidelines
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../DEVELOPMENT/" class="md-nav__link">
<span class="md-ellipsis">
Development Guide
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../HPC/" class="md-nav__link">
<span class="md-ellipsis">
HPC Guide
</span>
</a>
</li>
<li class="md-nav__item md-nav__item--active md-nav__item--nested">
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_5" checked>
<label class="md-nav__link" for="__nav_5" id="__nav_5_label" tabindex="0">
<span class="md-ellipsis">
Api
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_5_label" aria-expanded="true">
<label class="md-nav__title" for="__nav_5">
<span class="md-nav__icon md-icon"></span>
Api
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../analysis/" class="md-nav__link">
<span class="md-ellipsis">
Analysis &amp; Plotting Tools
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../environment/" class="md-nav__link">
<span class="md-ellipsis">
Brittle star environment
</span>
</a>
</li>
<li class="md-nav__item md-nav__item--active">
<input class="md-nav__toggle md-toggle" type="checkbox" id="__toc">
<label class="md-nav__link md-nav__link--active" for="__toc">
<span class="md-ellipsis">
Checkpoint &amp; Model Evaluation
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<a href="./" class="md-nav__link md-nav__link--active">
<span class="md-ellipsis">
Checkpoint &amp; Model Evaluation
</span>
</a>
<nav class="md-nav md-nav--secondary" aria-label="Table of contents">
<label class="md-nav__title" for="__toc">
<span class="md-nav__icon md-icon"></span>
Table of contents
</label>
<ul class="md-nav__list" data-md-component="toc" data-md-scrollfix>
<li class="md-nav__item">
<a href="#checkpoint-evaluation-during-training" class="md-nav__link">
<span class="md-ellipsis">
Checkpoint Evaluation (During Training)
</span>
</a>
<nav class="md-nav" aria-label="Checkpoint Evaluation (During Training)">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#configuration" class="md-nav__link">
<span class="md-ellipsis">
Configuration
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="#cross-model-fault-tolerance-analysis" class="md-nav__link">
<span class="md-ellipsis">
Cross-Model &amp; Fault Tolerance Analysis
</span>
</a>
<nav class="md-nav" aria-label="Cross-Model &amp; Fault Tolerance Analysis">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#csv-schema" class="md-nav__link">
<span class="md-ellipsis">
CSV Schema
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="#post-hoc-checkpoint-scanning" class="md-nav__link">
<span class="md-ellipsis">
Post-hoc Checkpoint Scanning
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="../simulation/" class="md-nav__link">
<span class="md-ellipsis">
Simulation &amp; Evaluation
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../tracking/" class="md-nav__link">
<span class="md-ellipsis">
Tracking &amp; Monitoring
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../training/" class="md-nav__link">
<span class="md-ellipsis">
Training Models
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_6" >
<label class="md-nav__link" for="__nav_6" id="__nav_6_label" tabindex="0">
<span class="md-ellipsis">
Design
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_6_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_6">
<span class="md-nav__icon md-icon"></span>
Design
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../design/actor-critic/" class="md-nav__link">
<span class="md-ellipsis">
Actor-Critic Architecture
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../design/communication/" class="md-nav__link">
<span class="md-ellipsis">
Communication scheme (Message Passing)
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../design/controllers/" class="md-nav__link">
<span class="md-ellipsis">
Levels of modularity and topology
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../design/input_action_spaces/" class="md-nav__link">
<span class="md-ellipsis">
Input (state) and output (action) spaces
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../design/learning_algorithm/" class="md-nav__link">
<span class="md-ellipsis">
Reinforcement Learning Algorithm
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../design/reward_function/" class="md-nav__link">
<span class="md-ellipsis">
Reward function and observation space
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_7" >
<label class="md-nav__link" for="__nav_7" id="__nav_7_label" tabindex="0">
<span class="md-ellipsis">
Scripts
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_7_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_7">
<span class="md-nav__icon md-icon"></span>
Scripts
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_7_1" >
<label class="md-nav__link" for="__nav_7_1" id="__nav_7_1_label" tabindex="0">
<span class="md-ellipsis">
Analysis
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="2" aria-labelledby="__nav_7_1_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_7_1">
<span class="md-nav__icon md-icon"></span>
Analysis
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../scripts/analysis/" class="md-nav__link">
<span class="md-ellipsis">
Experiment Analysis Tools
</span>
</a>
</li>
</ul>
</nav>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_8" >
<label class="md-nav__link" for="__nav_8" id="__nav_8_label" tabindex="0">
<span class="md-ellipsis">
Src
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_8_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_8">
<span class="md-nav__icon md-icon"></span>
Src
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_8_1" >
<label class="md-nav__link" for="__nav_8_1" id="__nav_8_1_label" tabindex="0">
<span class="md-ellipsis">
Experiment logger
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="2" aria-labelledby="__nav_8_1_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_8_1">
<span class="md-nav__icon md-icon"></span>
Experiment logger
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../src/experiment_logger/" class="md-nav__link">
<span class="md-ellipsis">
Experiment Logger
</span>
</a>
</li>
</ul>
</nav>
</li>
</ul>
</nav>
</li>
</ul>
</nav>
</div>
</div>
</div>
<div class="md-sidebar md-sidebar--secondary" data-md-component="sidebar" data-md-type="toc" >
<div class="md-sidebar__scrollwrap">
<div class="md-sidebar__inner">
<nav class="md-nav md-nav--secondary" aria-label="Table of contents">
<label class="md-nav__title" for="__toc">
<span class="md-nav__icon md-icon"></span>
Table of contents
</label>
<ul class="md-nav__list" data-md-component="toc" data-md-scrollfix>
<li class="md-nav__item">
<a href="#checkpoint-evaluation-during-training" class="md-nav__link">
<span class="md-ellipsis">
Checkpoint Evaluation (During Training)
</span>
</a>
<nav class="md-nav" aria-label="Checkpoint Evaluation (During Training)">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#configuration" class="md-nav__link">
<span class="md-ellipsis">
Configuration
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="#cross-model-fault-tolerance-analysis" class="md-nav__link">
<span class="md-ellipsis">
Cross-Model &amp; Fault Tolerance Analysis
</span>
</a>
<nav class="md-nav" aria-label="Cross-Model &amp; Fault Tolerance Analysis">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#csv-schema" class="md-nav__link">
<span class="md-ellipsis">
CSV Schema
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="#post-hoc-checkpoint-scanning" class="md-nav__link">
<span class="md-ellipsis">
Post-hoc Checkpoint Scanning
</span>
</a>
</li>
</ul>
</nav>
</div>
</div>
</div>
<div class="md-content" data-md-component="content">
<article class="md-content__inner md-typeset">
<h1 id="checkpoint-model-evaluation">Checkpoint &amp; Model Evaluation</h1>
<p>This guide covers how to evaluate trained brittle star models, with a focus on measuring defect tolerance (amputations) across different controller architectures.</p>
<h2 id="checkpoint-evaluation-during-training">Checkpoint Evaluation (During Training)</h2>
<p>The <code>PPOTrainer</code> can automatically evaluate every saved checkpoint using the fast MJX backend. This is enabled via configuration.</p>
<h3 id="configuration">Configuration</h3>
<p>In your experiment config or via CLI:
<div class="highlight"><pre><span></span><code>python<span class="w"> </span>scripts/train.py<span class="w"> </span>evaluation.evaluate_checkpoints<span class="o">=</span><span class="nb">true</span><span class="w"> </span>evaluation.eval_max_steps<span class="o">=</span><span class="m">5000</span>
</code></pre></div></p>
<p>Results are saved to <code>runs/&lt;run_dir&gt;/metrics/checkpoint_evaluation.csv</code> and synced to Weights &amp; Biases if enabled.</p>
<h2 id="cross-model-fault-tolerance-analysis">Cross-Model &amp; Fault Tolerance Analysis</h2>
<p>To measure how well different controllers handle damage (amputations), use <code>scripts/compare_models.py</code>. This script performs a grid search over models x morphologies.</p>
<ol>
<li>Create or update a YAML file in <code>configs/evaluation</code>.</li>
<li>Run the benchmark:</li>
</ol>
<div class="highlight"><pre><span></span><code>python<span class="w"> </span>scripts/compare_models.py<span class="w"> </span><span class="nv">evaluation</span><span class="o">=</span>poster
</code></pre></div>
<p>The script will evaluate every combination of model and morphology for the specified number of episodes.</p>
<p>The results are saved to a CSV (default: <code>metrics/model_comparison.csv</code>).</p>
<h3 id="csv-schema">CSV Schema</h3>
<table>
<thead>
<tr>
<th>Column</th>
<th>Description</th>
</tr>
</thead>
<tbody>
<tr>
<td><code>model_path</code></td>
<td>Path to the trained weights.</td>
</tr>
<tr>
<td><code>architecture</code></td>
<td>The <code>morph_mode</code> of the model (e.g., <code>CENTRALIZED</code>, <code>RING</code>).</td>
</tr>
<tr>
<td><code>arm_0</code> ... <code>arm_4</code></td>
<td>Number of segments in each arm slot (0 = amputated).</td>
</tr>
<tr>
<td><code>num_active_arms</code></td>
<td>Total number of arms with segments &gt; 0.</td>
</tr>
<tr>
<td><code>seed</code></td>
<td>The episode seed.</td>
</tr>
<tr>
<td><code>eval_return</code></td>
<td>Accumulated shaped reward.</td>
</tr>
<tr>
<td><code>approx_max_velocity</code></td>
<td>Average velocity: <code>(initial_dist - final_dist) / steps</code>.</td>
</tr>
<tr>
<td><code>reached_target</code></td>
<td>Whether the robot finished within the success radius.</td>
</tr>
</tbody>
</table>
<h2 id="post-hoc-checkpoint-scanning">Post-hoc Checkpoint Scanning</h2>
<p>If you need to re-evaluate every saved checkpoint in a run (e.g., to generate a learning curve with different metrics):</p>
<div class="highlight"><pre><span></span><code>python<span class="w"> </span>scripts/evaluate_checkpoints.py<span class="w"> </span><span class="se">\</span>
<span class="w"> </span>simulation.model_path<span class="o">=</span>runs/&lt;run_id&gt;/final_model.flax<span class="w"> </span><span class="se">\</span>
<span class="w"> </span>evaluation.eval_max_steps<span class="o">=</span><span class="m">2000</span>
</code></pre></div>
<p>This script scans the <code>checkpoints/</code> directory of the specified run and evaluates every <code>.flax</code> file it finds using the model's training morphology.</p>
</article>
</div>
<script>var target=document.getElementById(location.hash.slice(1));target&&target.name&&(target.checked=target.name.startsWith("__tabbed_"))</script>
</div>
</main>
<footer class="md-footer">
<div class="md-footer-meta md-typeset">
<div class="md-footer-meta__inner md-grid">
<div class="md-copyright">
Made with
<a href="https://squidfunk.github.io/mkdocs-material/" target="_blank" rel="noopener">
Material for MkDocs
</a>
</div>
</div>
</div>
</footer>
</div>
<div class="md-dialog" data-md-component="dialog">
<div class="md-dialog__inner md-typeset"></div>
</div>
<script id="__config" type="application/json">{"annotate": null, "base": "../..", "features": [], "search": "../../assets/javascripts/workers/search.2c215733.min.js", "tags": null, "translations": {"clipboard.copied": "Copied to clipboard", "clipboard.copy": "Copy to clipboard", "search.result.more.one": "1 more on this page", "search.result.more.other": "# more on this page", "search.result.none": "No matching documents", "search.result.one": "1 matching document", "search.result.other": "# matching documents", "search.result.placeholder": "Type to start searching", "search.result.term.missing": "Missing", "select.version": "Select version"}, "version": null}</script>
<script src="../../assets/javascripts/bundle.79ae519e.min.js"></script>
</body>
</html>