Skip to content

Page not found error during deployment #2

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
netlify-coding wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Page not found error during deployment #2

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 2 additions & 0 deletions netlify.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,2 @@
[build]
publish = "public"
248 changes: 248 additions & 0 deletions public/index.html
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,248 @@
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>Beam Weaver — Physics-informed RL for Photon Transport</title>
<style>
:root {
--bg: #0f1117;
--surface: #181b24;
--border: #2a2e3a;
--text: #e0e0e6;
--muted: #9a9caa;
--accent: #6c9cff;
--accent2: #a78bfa;
}
* { margin: 0; padding: 0; box-sizing: border-box; }
body {
font-family: -apple-system, BlinkMacSystemFont, "Segoe UI", Roboto, Helvetica, Arial, sans-serif;
background: var(--bg);
color: var(--text);
line-height: 1.7;
}
.container { max-width: 860px; margin: 0 auto; padding: 0 24px; }
header {
padding: 64px 0 40px;
text-align: center;
border-bottom: 1px solid var(--border);
}
header h1 {
font-size: 2.6rem;
font-weight: 700;
letter-spacing: -0.02em;
margin-bottom: 12px;
}
header .subtitle {
font-size: 1.15rem;
color: var(--muted);
max-width: 640px;
margin: 0 auto 24px;
}
.badges {
display: flex;
gap: 12px;
justify-content: center;
flex-wrap: wrap;
margin-bottom: 8px;
}
.badges img { height: 22px; }
.meta {
display: flex;
gap: 24px;
justify-content: center;
flex-wrap: wrap;
margin-top: 20px;
font-size: 0.9rem;
color: var(--muted);
}
.meta span { display: inline-flex; align-items: center; gap: 6px; }
section { padding: 40px 0; border-bottom: 1px solid var(--border); }
section:last-of-type { border-bottom: none; }
h2 {
font-size: 1.4rem;
font-weight: 600;
margin-bottom: 16px;
color: var(--accent);
}
p { margin-bottom: 14px; color: var(--text); }
ul { padding-left: 20px; margin-bottom: 14px; }
li { margin-bottom: 6px; color: var(--text); }
.card-grid {
display: grid;
grid-template-columns: repeat(auto-fit, minmax(200px, 1fr));
gap: 16px;
margin-top: 16px;
}
.card {
background: var(--surface);
border: 1px solid var(--border);
border-radius: 10px;
padding: 20px;
}
.card h3 {
font-size: 1rem;
font-weight: 600;
margin-bottom: 6px;
color: var(--accent2);
}
.card p { font-size: 0.9rem; color: var(--muted); margin-bottom: 0; }
a { color: var(--accent); text-decoration: none; }
a:hover { text-decoration: underline; }
.cta {
display: inline-block;
margin-top: 16px;
padding: 10px 24px;
background: var(--accent);
color: var(--bg);
border-radius: 8px;
font-weight: 600;
font-size: 0.95rem;
}
.cta:hover { opacity: 0.9; text-decoration: none; }
pre {
background: var(--surface);
border: 1px solid var(--border);
border-radius: 8px;
padding: 16px;
overflow-x: auto;
font-size: 0.88rem;
line-height: 1.6;
margin-bottom: 14px;
}
code { font-family: "SFMono-Regular", Consolas, "Liberation Mono", Menlo, monospace; }
.authors { margin-top: 16px; }
.authors .author { margin-bottom: 12px; }
.authors .name { font-weight: 600; }
.authors .affil { font-size: 0.9rem; color: var(--muted); }
footer {
padding: 32px 0;
text-align: center;
font-size: 0.85rem;
color: var(--muted);
}
blockquote {
border-left: 3px solid var(--accent2);
padding: 12px 16px;
margin-bottom: 14px;
background: var(--surface);
border-radius: 0 8px 8px 0;
color: var(--muted);
font-size: 0.95rem;
}
</style>
</head>
<body>
<div class="container">
<header>
<h1>Beam Weaver</h1>
<p class="subtitle">Physics-informed n-step reinforcement learning for stochastic photon transport in water</p>
<div class="badges">
<a href="https://doi.org/10.5281/zenodo.18994135"><img src="https://zenodo.org/badge/DOI/10.5281/zenodo.18994135.svg" alt="DOI"></a>
<a href="https://joss.theoj.org/papers/048f725c9d7ad766994683f478dbccd9"><img src="https://joss.theoj.org/papers/048f725c9d7ad766994683f478dbccd9/status.svg" alt="JOSS status"></a>
</div>
<div class="meta">
<span>Status: research prototype</span>
<span>License: Apache-2.0</span>
<span>Domain: radiation transport &amp; AI</span>
</div>
</header>

<section>
<blockquote>
Beam Weaver is a research software prototype for learning event-by-event photon transport in a homogeneous water phantom. It combines a custom Monte Carlo reference simulator, a physics-informed n-step Soft Actor-Critic reinforcement learning environment, and evaluation tools that compare learned particle histories against conventional transport outputs.
</blockquote>
</section>

<section>
<h2>What Beam Weaver Does</h2>
<p>Beam Weaver explores whether a <strong>Soft Actor-Critic (SAC)</strong> agent can learn the stochastic logic of photon transport in water at the <strong>event level</strong>, rather than only predicting final observables.</p>
<p>For each photon history, the code predicts:</p>
<ul>
<li>The next interaction type</li>
<li>The distance to the next interaction</li>
<li>Scattering geometry</li>
<li>The outgoing photon state</li>
<li>The number, energy, and direction of secondary particles</li>
</ul>
<p>This makes Beam Weaver a <strong>learned transport-engine prototype</strong> rather than a generic machine-learning regressor.</p>
</section>

<section>
<h2>Photon Interactions Modeled</h2>
<div class="card-grid">
<div class="card">
<h3>Rayleigh Scattering</h3>
<p>Coherent scattering with energy-dependent form factors for water.</p>
</div>
<div class="card">
<h3>Compton Scattering</h3>
<p>Incoherent scattering with recoil electron kinematics.</p>
</div>
<div class="card">
<h3>Photoelectric Absorption</h3>
<p>Shell-specific absorption with electron emission.</p>
</div>
<div class="card">
<h3>Pair Production</h3>
<p>Electron-positron pair creation with energy sharing.</p>
</div>
</div>
</section>

<section>
<h2>Training Architecture</h2>
<p>Beam Weaver is trained in two stages:</p>
<ul>
<li><strong>Stage I — Pretraining:</strong> Supervised learning of a multi-head physics branch on Monte Carlo-generated labels (interaction type, free path, scattering angles, secondary particles).</li>
<li><strong>Stage II — Curriculum RL:</strong> A five-phase curriculum that progressively transitions from teacher-forced Monte Carlo supervision to autonomous policy learning using a hybrid n-step SAC framework.</li>
</ul>
<p>The RL objective is physics-regularized, combining the standard SAC loss with auxiliary physics losses for energy, angle, and interaction-type consistency.</p>
</section>

<section>
<h2>Quick Start</h2>
<pre><code># Create environment
conda env create -f environment.yml
conda activate beam-weaver

# Or with pip
python -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt

# Run Beam Weaver
python Beam_weaver_0.1.0.py</code></pre>
<p>The script is interactive and supports: generating Monte Carlo data, pretraining the physics head, training a SAC model, evaluating trained models, and comparing MC vs. agent outputs.</p>
</section>

<section>
<h2>Authors</h2>
<div class="authors">
<div class="author">
<div class="name">Pedro Teles</div>
<div class="affil">Assistant Professor, Department of Physics and Astronomy, Faculty of Sciences, University of Porto</div>
</div>
<div class="author">
<div class="name">João Melo</div>
<div class="affil">MSc Student in Medical Physics, Department of Physics and Astronomy, Faculty of Sciences, University of Porto</div>
</div>
</div>
</section>

<section>
<h2>References</h2>
<ul>
<li>F. Salvat. <em>PENELOPE-2018: A Code System for Monte Carlo Simulation of Electron and Photon Transport.</em> OECD/NEA, 2019.</li>
<li>T. Haarnoja et al. <em>Soft Actor-Critic: Off-Policy Maximum Entropy Deep RL with a Stochastic Actor.</em> ICML, 2018.</li>
<li>A. Raffin et al. <em>Stable-Baselines3: Reliable RL Implementations.</em> JMLR, 22:1–8, 2021.</li>
<li>J. H. Hubbell et al. <em>Atomic Form Factors, Incoherent Scattering Functions, and Photon Scattering Cross Sections.</em> J. Phys. Chem. Ref. Data, 4(3), 1975.</li>
</ul>
</section>

<footer>
<p>Beam Weaver is released under the Apache License 2.0. Third-party data and dependencies remain under their respective licenses.</p>
</footer>
</div>
</body>
</html>