gomoku_rl.utils.eval module

gomoku_rl.utils.eval.eval_win_rate(env: GomokuEnv, player_black: Callable[[TensorDict], TensorDict], player_white: Callable[[TensorDict], TensorDict], n: int = 1)

gomoku_rl.utils.eval.get_payoff_matrix(env: GomokuEnv, row_policies: list[Callable[[TensorDict], TensorDict]], col_policies: list[Callable[[TensorDict], TensorDict]], n: int = 1)