Skip to content

Conversation

@luccabb
Copy link
Owner

@luccabb luccabb commented Jan 22, 2026

  • Add moonfish.rl module with ChessEnvironment for RL training
  • FastAPI server with /reset, /step, /state, /engine-move endpoints
  • Web UI to play against Moonfish in the browser
  • Cerebellum opening book integration
  • Deploy to HuggingFace Spaces: huggingface.co/spaces/luccabb/moonfish_chess
  • Update README with Play Online link and RL documentation
  • Add [rl] optional dependencies to pyproject.toml

@luccabb luccabb force-pushed the add-rl-environment branch 2 times, most recently from 2b762bb to 99e9f9c Compare January 22, 2026 09:28
This adds a chess reinforcement learning environment following the
OpenEnv interface pattern, with both local and HTTP client-server modes.

Features:
- ChessEnvironment class with configurable rewards, opponents, and game limits
- FastAPI server with REST endpoints (/reset, /step, /state, /engine-move)
- HTTP client for remote environment access
- Web UI for playing against the engine
- HuggingFace Spaces deployment configuration (Dockerfile, openenv.yaml)
- Example training scripts for local and remote usage

Also includes:
- mypy configuration for optional RL dependencies
- Import formatting fixes for ufmt compliance
@luccabb luccabb force-pushed the add-rl-environment branch from 9b5594a to 76801d8 Compare January 22, 2026 09:39
@luccabb luccabb merged commit 204c439 into master Jan 22, 2026
10 checks passed
@luccabb luccabb deleted the add-rl-environment branch January 22, 2026 20:23
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants