Spaces:

ARotting
/

microzero-play

Running

App Files Files Community

microzero-play / index.html

ARotting

Publish Playable neural MCTS Tic-Tac-Toe agent

c7928dd verified 2 days ago

Raw

History Blame Contribute Delete

11.5 kB

	<!doctype html>
	<html lang="en">
	<head>
	<meta charset="utf-8">
	<meta name="viewport" content="width=device-width,initial-scale=1">
	<title>Microzero Play</title>
	<style>
	:root { color-scheme: dark; font-family: Inter, ui-sans-serif, system-ui; }
	* { box-sizing: border-box; }
	body { margin: 0; min-height: 100vh; background: #060817; color: #edf4ff; }
	canvas { position: fixed; inset: 0; width: 100%; height: 100%; opacity: .55; }
	main { position: relative; z-index: 1; width: min(1080px, 92vw); margin: auto;
	padding: 72px 0 96px; }
	.eyebrow { color: #73e6ff; letter-spacing: .18em; text-transform: uppercase;
	font-size: .75rem; font-weight: 800; }
	h1 { font-size: clamp(3rem, 8vw, 7rem); line-height: .9; margin: 14px 0 24px;
	background: linear-gradient(120deg,#fff,#74e7ff 55%,#b48cff);
	-webkit-background-clip: text; color: transparent; }
	.lead { max-width: 760px; color: #b8c7e6; font-size: 1.2rem; line-height: 1.65; }
	.actions { display: flex; flex-wrap: wrap; gap: 12px; margin: 30px 0 48px; }
	a { color: inherit; }
	.button { padding: 12px 18px; border-radius: 999px; text-decoration: none;
	background: #eaf8ff; color: #07101c; font-weight: 800; }
	.button.alt { background: #171d38cc; color: #dce8ff; border: 1px solid #415078; }
	.grid { display: grid; grid-template-columns: 1.1fr .9fr; gap: 20px; }
	.card { border: 1px solid #344269; background: #0c1128dd; border-radius: 24px;
	padding: 24px; backdrop-filter: blur(18px); box-shadow: 0 24px 80px #0008; }
	h2 { margin-top: 0; }
	pre { white-space: pre-wrap; word-break: break-word; color: #a9bddf;
	max-height: 520px; overflow: auto; }
	ul { max-height: 520px; overflow: auto; padding-left: 1.2rem; color: #a9bddf; }
	li { margin: 8px 0; }
	input { width: 100%; padding: 12px; border-radius: 12px; border: 1px solid #344269;
	background: #070b1a; color: white; margin-bottom: 12px; }
	@media (max-width: 780px) { .grid { grid-template-columns: 1fr; } }
	</style>
	</head>
	<body>
	<canvas id="field"></canvas>
	<main>
	<div class="eyebrow">Jacob Garcia · Hugging Face Model Foundry</div>
	<h1>Microzero Play</h1>
	<p class="lead">Playable neural MCTS Tic-Tac-Toe agent. This showcase backs up the
	trained artifacts, measured evaluation, and complete runnable source.</p>
	<div class="actions">
	<a class="button" href="https://huggingface.co/spaces/ARotting/microzero-play/tree/main">Explore every file</a>
	<a class="button alt" href="https://huggingface.co/ARotting">View the full foundry</a>
	</div>
	<div class="grid">
	<section class="card">
	<h2>Verified project card</h2>
	<pre># MicroZero

	MicroZero is a tiny AlphaZero-style Tic-Tac-Toe agent. A shared neural trunk predicts
	both move priors and position value. Monte Carlo Tree Search converts those estimates
	into stronger self-play targets, while terminal outcomes supervise value learning.

	The training loop uses:

	- neural-guided PUCT search;
	- root Dirichlet exploration;
	- policy targets from MCTS visit counts;
	- terminal win/draw/loss value targets;
	- all eight square-board symmetries;
	- a bounded replay buffer.

	Evaluation alternates playing first and second against random and exact minimax
	opponents.

	## Verified results

	- 7,626 trainable parameters;
	- 980 neural-MCTS self-play games;
	- 24,000-example bounded replay buffer after symmetry augmentation;
	- 384 wins, 16 draws, and zero losses over 400 games against random play;
	- 200 draws and zero losses over 200 games against exact minimax.

	The exact opponent is used only for final evaluation, not as a source of training
	targets. Full metrics and the per-iteration learning history are stored in
	`artifacts/microzero/evaluation.json`.

	## Reproduce

	```powershell
	uv run python projects/microzero/train.py
	```
	</pre>
	<h2>Evaluation snapshot</h2>
	<pre>{
	"model": "MicroZero",
	"parameters": 7626,
	"self_play_iterations": 14,
	"self_play_games": 980,
	"final_replay_examples": 24000,
	"training_history": [
	{
	"iteration": 1,
	"replay_examples": 4128,
	"x_win_rate": 0.5428571428571428,
	"o_win_rate": 0.14285714285714285,
	"draw_rate": 0.3142857142857143,
	"average_game_moves": 7.371428571428571,
	"policy_loss": 2.1499555636854732,
	"value_loss": 0.5162482239744243
	},
	{
	"iteration": 2,
	"replay_examples": 8128,
	"x_win_rate": 0.5142857142857142,
	"o_win_rate": 0.0,
	"draw_rate": 0.4857142857142857,
	"average_game_moves": 7.142857142857143,
	"policy_loss": 1.9038925133645535,
	"value_loss": 0.3203776921145618
	},
	{
	"iteration": 3,
	"replay_examples": 12328,
	"x_win_rate": 0.42857142857142855,
	"o_win_rate": 0.014285714285714285,
	"draw_rate": 0.5571428571428572,
	"average_game_moves": 7.5,
	"policy_loss": 1.4543613067695074,
	"value_loss": 0.26955098012576295
	},
	{
	"iteration": 4,
	"replay_examples": 16456,
	"x_win_rate": 0.5142857142857142,
	"o_win_rate": 0.0,
	"draw_rate": 0.4857142857142857,
	"average_game_moves": 7.371428571428571,
	"policy_loss": 1.229265012878638,
	"value_loss": 0.22285609325537314
	},
	{
	"iteration": 5,
	"replay_examples": 20952,
	"x_win_rate": 0.2857142857142857,
	"o_win_rate": 0.0,
	"draw_rate": 0.7142857142857143,
	"average_game_moves": 8.028571428571428,
	"policy_loss": 1.1138035529633847,
	"value_loss": 0.1854344406960214
	},
	{
	"iteration": 6,
	"replay_examples": 24000,
	"x_win_rate": 0.3142857142857143,
	"o_win_rate": 0.014285714285714285,
	"draw_rate": 0.6714285714285714,
	"average_game_moves": 7.957142857142857,
	"policy_loss": 1.0146886479664357,
	"value_loss": 0.15539901554980812
	},
	{
	"iteration": 7,
	"replay_examples": 24000,
	"x_win_rate": 0.2571428571428571,
	"o_win_rate": 0.0,
	"draw_rate": 0.7428571428571429,
	"average_game_moves": 8.085714285714285,
	"policy_loss": 0.8795330280319174,
	"value_loss": 0.11288299490796759
	},
	{
	"iteration": 8,
	"replay_examples": 24000,
	"x_win_rate": 0.24285714285714285,
	"o_win_rate": 0.0,
	"draw_rate": 0.7571428571428571,
	"average_game_moves": 8.314285714285715,
	"policy_loss": 0.7982094690520712,
	"value_loss": 0.09204166978993948
	},
	{
	"iteration": 9,
	"replay_examples": 24000,
	"x_win_rate": 0.3,
	"o_win_rate": 0.014285714285714285,
	"draw_rate": 0.6857142857142857,
	"average_game_moves": 7.985714285714286,
	"policy_loss": 0.7609958442601752,
	"value_loss": 0.09048273768077822
	},
	{
	"iteration": 10,
	"replay_examples": 24000,
	"x_win_rate": 0.2857142857142857,
	"o_win_rate": 0.0,
	"draw_rate": 0.7142857142857143,
	"average_game_moves": 8.17142857142857,
	"policy_loss": 0.7380844823857571,
	"value_loss": 0.08676699136799955
	},
	{
	"iteration": 11,
	"replay_examples": 24000,
	"x_win_rate": 0.18571428571428572,
	"o_win_rate": 0.0,
	"draw_rate": 0.8142857142857143,
	"average_game_moves": 8.371428571428572,
	"policy_loss": 0.7269294456915653,
	"value_loss": 0.074583658938633
	},
	{
	"iteration": 12,
	"replay_examples": 24000,
	"x_win_rate": 0.3142857142857143,
	"o_win_rate": 0.0,
	"draw_rate": 0.6857142857142857,
	"average_game_moves": 8.142857142857142,
	"policy_loss": 0.7146875767948779,
	"value_loss": 0.07327091548235175
	},
	{
	"iteration": 13,
	"replay_examples": 24000,
	"x_win_rate": 0.22857142857142856,
	"o_win_rate": 0.0,
	"draw_rate": 0.7714285714285715,
	"average_game_moves": 8.17142857142857,
	"policy_loss": 0.7104355310823055,
	"value_loss": 0.07133727120433717
	},
	{
	"iteration": 14,
	"replay_examples": 24000,
	"x_win_rate": 0.2,
	"o_win_rate": 0.0,
	"draw_rate": 0.8,
	"average_game_moves": 8.371428571428572,
	"policy_loss": 0.7074488862714869,
	"value_loss": 0.06895742299867437
	}
	],
	"versus_random": {
	"games": 400,
	"wins": 384,
	"draws": 16,
	"losses": 0,
	"win_rate": 0.96,
	"non_loss_rate": 1.0,
	"average_moves": 6.065
	},
	"versus_exact_minimax": {
	"games": 200,
	"wins": 0,
	"draws": 200,
	"losses": 0,
	"win_rate": 0.0,
	"non_loss_rate": 1.0,
	"average_moves": 9.0
	}
	}</pre>
	</section>
	<section class="card">
	<h2>Backed-up artifact tree</h2>
	<input id="filter" placeholder="Filter files…" autocomplete="off">
	<ul id="files"><li><code>README.md</code></li>
	<li><code>__pycache__/app.cpython-311.pyc</code></li>
	<li><code>__pycache__/game.cpython-311.pyc</code></li>
	<li><code>__pycache__/mcts.cpython-311.pyc</code></li>
	<li><code>__pycache__/model.cpython-311.pyc</code></li>
	<li><code>__pycache__/train.cpython-311.pyc</code></li>
	<li><code>app.py</code></li>
	<li><code>artifacts/microzero/evaluation.json</code></li>
	<li><code>artifacts/microzero/model.safetensors</code></li>
	<li><code>game.py</code></li>
	<li><code>mcts.py</code></li>
	<li><code>model.py</code></li>
	<li><code>requirements.txt</code></li>
	<li><code>train.py</code></li></ul>
	</section>
	</div>
	</main>
	<script>
	const canvas=document.querySelector('#field'),ctx=canvas.getContext('2d');
	let dots=[];
	function resize(){canvas.width=innerWidth;canvas.height=innerHeight;
	dots=Array.from({length:90},()=>({x:Math.random()*innerWidth,
	y:Math.random()innerHeight,vx:(Math.random()-.5).35,vy:(Math.random()-.5)*.35}));}
	function draw(){ctx.clearRect(0,0,canvas.width,canvas.height);
	for(const d of dots){d.x=(d.x+d.vx+innerWidth)%innerWidth;
	d.y=(d.y+d.vy+innerHeight)%innerHeight;ctx.fillStyle='#65dcff99';
	ctx.beginPath();ctx.arc(d.x,d.y,1.4,0,7);ctx.fill();}requestAnimationFrame(draw);}
	addEventListener('resize',resize);resize();draw();
	document.querySelector('#filter').addEventListener('input',e=>{
	const q=e.target.value.toLowerCase();for(const li of document.querySelectorAll('li'))
	li.hidden=!li.textContent.toLowerCase().includes(q);});
	</script>
	</body>
	</html>