def _minimax(self, root_move: tuple[int, int], depth: int,
game: ReversiGame, alpha: float, beta: float) -> GameTree:
"""
_minimax is a minimax function with alpha-beta pruning implemented that returns
a full GameTree where each node stores the given evaluation
Preconditions
- depth >= 0
"""
white_move = (game.get_current_player() == -1)
ret = GameTree(move=root_move, is_white_move=white_move)
# early return at max depth
if depth == self.depth:
ret.evaluation = heuristic(game, self.heuristic_list)
return ret
possible_moves = list(game.get_valid_moves())
if not possible_moves:
if game.get_winner() == 'white':
ret.evaluation = 10000
elif game.get_winner() == 'black':
ret.evaluation = -10000
else:
ret.evaluation = 0
return ret
random.shuffle(possible_moves)
best_value = float('-inf')
if not white_move:
best_value = float('inf')
for move in possible_moves:
new_game = game.copy_and_make_move(move)
new_tree = self._minimax(move, depth + 1, new_game, alpha, beta)
ret.add_subtree(new_tree)
# we update the alpha value when the maximizer is playing (white)
if white_move and best_value < new_tree.evaluation:
best_value = new_tree.evaluation
alpha = max(alpha, best_value)
if beta <= alpha:
break
# we update the beta value when the minimizer is playing (black)
elif not white_move and best_value > new_tree.evaluation:
best_value = new_tree.evaluation
beta = min(beta, best_value)
if beta <= alpha:
break
ret.evaluation = best_value
return ret
def _minimax(self, root_move: tuple[int, int], game: ReversiGame,
depth: int) -> GameTree:
"""
_minimax is a function that returns a tree where each node has a value determined by
the minimax search algorithm
"""
white_move = (game.get_current_player() == -1)
ret = GameTree(move=root_move, is_white_move=white_move)
# early return if we have reached max depth
if depth == self.depth:
ret.evaluation = heuristic(game, self.heuristic_list)
return ret
possible_moves = list(game.get_valid_moves())
# game is over if there are no possible moves in a position
if not possible_moves:
# if there are no moves, then the game is over so we check for the winner
if game.get_winner() == 'white':
ret.evaluation = 10000
elif game.get_winner() == 'black':
ret.evaluation = -10000
else:
ret.evaluation = 0
return ret
# shuffle for randomness
random.shuffle(possible_moves)
# best_value tracks the best possible move that the player can make
# this value is maximized by white and minimized by black
best_value = float('-inf')
if not white_move:
best_value = float('inf')
for move in possible_moves:
new_game = game.copy_and_make_move(move)
new_subtree = self._minimax(move, new_game, depth + 1)
if white_move:
best_value = max(best_value, new_subtree.evaluation)
else:
best_value = min(best_value, new_subtree.evaluation)
ret.add_subtree(new_subtree)
# update the evaluation value of the tree once all subtrees are added
ret.evaluation = best_value
return ret