Add chess puzzle solving environment, tools, and rewards #18
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
added 2 commits
January 22, 2026 21:07
- ChessPuzzleEnv: Non-Docker environment using python-chess + Stockfish - Supports Lichess puzzle format (FEN + solution moves) - Move parsing in both UCI and SAN formats - Board visualization and state tracking - Chess tools: chess_move, chess_get_state, chess_get_legal_moves - Stateful tools with environment pooling (pool_size=8) - Chess rewards: - chess_puzzle_reward: Dense reward based on Stockfish centipawn evaluation - chess_puzzle_reward_simple: Binary reward (solved/not solved) - Data utilities: Load puzzles from Lichess CSV or JSONL format - Unit tests for the chess environment
- scripts/train_chess.sh: Training script with hyperparameters for chess puzzle RL - scripts/prepare_chess_data.py: Convert Lichess CSV to training format - data/chess/: Sample train/val puzzles (10 train, 5 val) - chess_readme.MD: Quick start guide and configuration reference
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
ChessPuzzleEnv: Non-Docker environment using python-chess + Stockfish
Chess tools: chess_move, chess_get_state, chess_get_legal_moves
Chess rewards:
Data utilities: Load puzzles from Lichess CSV or JSONL format
Unit tests for the chess environment