Downloads · 30 days
0
chess-alphazero-openenv
yogeshwaran13/chess-alphazero-openenv
chess-alphazero-openenv is a reinforcement learning model from yogeshwaran13. Use it for the reinforcement learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
AlphaZero-style chess agent using MCTS + ResNet self-play.
Access
Public
Updated Mar 28, 2026
Repo size
239 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt239 MB · 100%
At a glance
- Task
- Reinforcement Learning
- License
- mit
- Access
- Public
- Created
- Mar 28, 2026
- Updated
- Mar 28, 2026
- SHA
- 546632cc
Model card
From the Hugging Face model README
♟️ Chess AlphaZero — OpenEnv
AlphaZero-style chess agent using MCTS + ResNet self-play.
Architecture
- ResNet: 5 residual blocks, 64 channels
- Input : 19 × 8 × 8 board tensor
- Output: Policy (4096 moves) + Value (-1 to +1)
Training Results
- Final Policy Loss : 1.4836
- Final Value Loss : 0.0030
- Avg Game Length : 34.0 moves
- Total Iterations : 20
Usage
import torch
net = ChessNet(in_channels=19, channels=64, num_res_blocks=5)
ckpt = torch.load("chess_alphazero_final.pt")
net.load_state_dict(ckpt["model"])
net.eval()
- Task
- Reinforcement Learning
- License
- mit
- Languages
- en
- Created
- Mar 28, 2026
- Updated
- Mar 28, 2026