RL lab
This is the handoff to the reinforcement-learning bot. Positions are legal FEN from chess.js. Ranking today is material swing and length — not ACPL. Wire Stockfish later; do not pretend the rules engine is an evaluator.
Export JSON
{
"schema": "positions[i] is the board before positions[i].moveUci",
"engine": "none — Stockfish ACPL is the next pipe",
"games": [{ "coachColor": "w", "result": "1-0", "positions": [...] }]
}Training-value ranking
Instructive first, then largest material imbalance, then longer games. Use this list to pick what the bot should see next.
White vs Black
? · 5 ply · Oct 13, 2020
White vs Black
Borg Defense: Borg Gambit · 54 ply · Oct 28, 2020
White vs Black
Zukertort Opening: Kingside Fianchetto · 29 ply · Oct 27, 2020
White vs Black
? · 5 ply · Oct 12, 2020
White vs Black
? · 3 ply · Oct 28, 2020
White vs Black
Alekhine Defense: Scandinavian Variation, Geschev Gambit · 30 ply · Aug 16, 2020
White vs Black
? · 5 ply · Jul 22, 2021
White vs Black
? · 5 ply · Oct 28, 2020
White vs Black
? · 1 ply · Jun 17, 2021
White vs Black
? · 29 ply · May 10, 2021
White vs Black
? · 13 ply · Oct 28, 2020
White vs Black
King's Gambit Declined: Queen's Knight Defense · 83 ply · Dec 3, 2020
White vs Black
? · 67 ply · Oct 13, 2020
White vs Black
Hungarian Opening: Myers Defense · 50 ply · Aug 17, 2020
White vs Black
Pirc Defense: Austrian Attack, Ljubojevic Variation · 34 ply · May 16, 2024
White vs Black
Polish Opening: Karniewski Variation · 23 ply · Oct 28, 2020