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 <noreply@anthropic.com>

1 files changed, 3 insertions, 1 deletions

diff --git a/.gitignore b/.gitignore
index 52b5187..5016e06 100644
--- a/.gitignore
+++ b/.gitignore
@@ -9,4 +9,6 @@
 /.direnv
 
 # Temporary removing github workflows
-.github
\ No newline at end of file
+.github
+# Trained networks (cargo run --release -- train)
+/weights