From 94f3df190a91898eb344b9214a57eb31792bcb1c Mon Sep 17 00:00:00 2001 From: Dylan Date: Thu, 5 Nov 2026 13:46:28 +1300 Subject: feat: Neural network opponent trained by self-play - 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 --- src/claude-player.rs | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'src/claude-player.rs') diff --git a/src/claude-player.rs b/src/claude-player.rs index 5cbd794..c25c5e1 100644 --- a/src/claude-player.rs +++ b/src/claude-player.rs @@ -39,7 +39,7 @@ impl MinimaxPlayer for ClaudePlayer /// - jumps the tigers could make right now (sheep left hanging); /// - tigers boxed in with no move at all, since trapping every tiger wins for the sheep; /// - tiger mobility in general, since the sheep win by squeezing it to zero. - fn evaluate(&mut self, board: &GameBoard) -> f32 + fn evaluate(&mut self, board: &GameBoard, _turn: Turn) -> f32 { let dead = TOTAL_SHEEP - board.sheep_count() - board.sheep_left(); -- cgit v1.3.1