Skip to content
Michael Pang edited this page Dec 19, 2017 · 2 revisions

I'll write the bugs I found here in case I have to rebase:

  1. Evaluate: when automatically drawing a long game, it counts as a win for one player! Really bad
  2. ChessPlayer: doesn't reset MCTS nodes in between moves. It's like keeping the hash table of moves, except it messes up MCTS node statistics with transpositions.
  3. Optimize: I just realized I was training everything on the starting position... ALWAYS VALIDATE INPUT DATA
  4. (minor) SL needlessly loads model