feat: Multi-threaded training; play matches every 10 generations

2026-11-09T03:38:13Z

Gradients and losses are computed on rayon's pool in fixed-size chunks summed in order, so the weights are the same on any number of threads. Self-play uses the same pool, and the output shows the training time. The matches against the earlier network and ClaudePlayer now run only every --match-every generations (default 10), against the generation that last played them, read back from its saved file. Co-Authored-By: Claude Opus 5.5

feat: Neural network opponent trained by self-play

2026-11-05T00:46:28Z

- 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

boss/tigers-and-sheep.git/src/network.rs, branch master

feat: Multi-threaded training; play matches every 10 generations

feat: Neural network opponent trained by self-play