| Commit message (Collapse) | Author | Age | Files | Lines | |
|---|---|---|---|---|---|
| * | feat: Draw by threefold repetition | Dylan | 18 hours | 1 | -2/+2 |
| | | | | | | | | | | | A position coming up for the third time with the same side to move ends the game as a draw, in the TUI and in training self-play. Players now get the game's earlier boards in pick_move, and the search scores the first repetition on its path as a draw, so a side that is ahead avoids one and a side that is behind seeks one. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> | ||||
| * | feat: Neural network opponent trained by self-play | Dylan | 5 days | 1 | -0/+68 |
| - NeuralPlayer: a MinimaxPlayer that scores positions with a small MLP (network.rs, hand-written backprop and Adam, no new dependencies) - train subcommand: self-play with TD(lambda) targets, cut at random exploration moves so sheep blunders don't bias the net towards tigers - neural subcommand: play against a trained network - evaluate now gets the side to move - Board symmetries; the search cache keys by the canonical board, which halves the depth-9 bench time with identical moves and scores Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> | |||||
 |
index : boss/tigers-and-sheep.git | |
| Unnamed repository; edit this file 'description' to name the repository. |
| summaryrefslogtreecommitdiff |