alphazero-connect4

AlphaZero-style Connect Four agent

Policy/value ResNet trained from zero human knowledge by self-play + MCTS (AlphaZero-style) on the standard 6x7 Connect Four board.

Play against it here: connect4-arena Space

Model

Training

• Self-play with the latest network: batched MCTS (lockstep games, one GPU forward per tick), Dirichlet root noise (alpha=1.0, eps=0.25), tau=1 sampling for the first 10 plies.
• Replay buffer with horizontal-flip augmentation at sample time; loss = soft-target cross-entropy + value MSE, AdamW (lr 1e-3, wd 1e-4).
• Gating: a candidate replaces the published best only on >55% score over arena games vs. the current best.
• 150 iterations, 19,200 self-play games, 7.9 h wallclock.

Evaluation (final iteration, real numbers)

Elo anchored at random agent = 0; pure-MCTS-200 anchor calibrated by ladder matches at 989 Elo.

Usage

from az.model import create_model  # az package: see the Space's bundled copy
import json, torch
from safetensors.torch import load_file

model = create_model(json.load(open("config.json")))
model.load_state_dict(load_file("model.safetensors"))

Limitations

• Connect Four is solved (first player wins with perfect play); this agent is strong but not perfect — deep tactics beyond its search budget can beat it.
• Trained only for the standard 6x7 board.
• The 40-game gating/eval matches carry ~8% sampling noise per point; the Elo curve's fine structure is noisy even though the trend is real.

Source repository

程式碼、訓練與評估流程、測試與完整證據都在 GitHub：https://github.com/kuotunyu/alphazero-connect4。GitHub kuotunyu 與 Hugging Face steven0226 為同一人。

Source code, the training/evaluation pipeline, tests and the full evidence trail live at https://github.com/kuotunyu/alphazero-connect4. GitHub kuotunyu and Hugging Face steven0226 are the same author.