bupticybee/icyChessZero
A Chinese chess AI trained with AlphaGo Zero-style self-play reinforcement learning and deep neural networks.
Not currently ranked — collecting fresh signals.
star history
This project applies the AlphaGo Zero methodology to Chinese chess, using deep neural networks combined with Monte Carlo Tree Search and self-play reinforcement learning to train a competitive chess-playing agent. The system supports distributed training across multiple machines for scalable compute, and tracks ELO ratings to measure progress toward human intermediate+ skill levels.
Frequently asked
- What is bupticybee/icyChessZero?
- A Chinese chess AI trained with AlphaGo Zero-style self-play reinforcement learning and deep neural networks.
- Is icyChessZero open source?
- Yes — bupticybee/icyChessZero is open source, released under the MIT license.
- What language is icyChessZero written in?
- bupticybee/icyChessZero is primarily written in Jupyter Notebook.
- How popular is icyChessZero?
- bupticybee/icyChessZero has 420 stars on GitHub.
- Where can I find icyChessZero?
- bupticybee/icyChessZero is on GitHub at https://github.com/bupticybee/icyChessZero.