def _value_eval(self, game: ReversiGame, piece: str) -> Union[float, int]:
"""The evaluation function for minimax. For Positional Player, the evaluation function
will evaluate the positional advantage of the pieces on the board.
Preconditions:
- piece in {BLACK, WHITE}
:param game: the current game state for evaluation
:return: value evaluated from the current game state
"""
if game.get_winner() is not None:
if game.get_winner() == piece: # win
return math.inf
elif game.get_winner() == 'Draw': # draw
return 0
else: # lose
return -math.inf
else:
num_black, num_white = game.get_num_pieces(
)[BLACK], game.get_num_pieces()[WHITE]
corner_black, corner_white = check_corners(game)
board_filled = (num_black + num_white) / (game.get_size()**2)
if piece == BLACK:
if board_filled < 0.80: # early to middle game
return 10 * (corner_black - corner_white) + len(
game.get_valid_moves())
else: # end game
return num_black / num_white
else:
if board_filled < 0.80: # early to middle game
return 10 * (corner_white - corner_black) + len(
game.get_valid_moves())
else: # end game
return num_white / num_black
def test_players(player1: Player, player2: Player, iterations: int) -> None:
"""
test_players is a function that runs <iterations> number of games between player1
and player2
"""
white = 0
black = 0
ties = 0
for _ in range(iterations):
game = ReversiGame()
prev_move = (-1, -1)
while game.get_winner() is None:
move = player1.make_move(game, prev_move)
game.try_make_move(move)
if game.get_winner() is None:
prev_move = player2.make_move(game, move)
game.try_make_move(prev_move)
if game.get_winner() == 'white':
print('White WINS')
white += 1
elif game.get_winner() == 'black':
print('Black WINS')
black += 1
else:
print('TIE')
ties += 1
print("Player 1 Wins: " + str(black))
print("Player 2 Wins: " + str(white))
def _run_ai_simulation(game_surface: pygame.Surface, size: int,
player1: Union[MobilityTreePlayer, PositionalTreePlayer, RandomPlayer,
ReversiGame, MCTSTimeSavingPlayer],
player2: Union[MobilityTreePlayer, PositionalTreePlayer, RandomPlayer,
ReversiGame, MCTSTimeSavingPlayer]) -> None:
if size == 8:
background = pygame.image.load('assets/gameboard8.png')
elif size == 6:
background = pygame.image.load('assets/gameboard6.png')
else:
raise ValueError("invalid size.")
game_surface.blit(background, (0, 0))
pygame.display.flip()
game = ReversiGame(size)
previous_move = '*'
board = game.get_game_board()
_draw_game_state(game_surface, background, size, board)
pass_move = pygame.image.load('assets/pass.png')
player1_side = BLACK
while game.get_winner() is None:
if previous_move == '*' or game.get_current_player() == player1_side:
move = player1.make_move(game, previous_move)
else:
move = player2.make_move(game, previous_move)
previous_move = move
game.make_move(move)
if move == 'pass':
surface = game_surface
game_surface.blit(pass_move, (300, 300))
pygame.display.flip()
pygame.time.wait(500)
game_surface.blit(surface, (0, 0))
pygame.display.flip()
else:
board = game.get_game_board()
_draw_game_state(game_surface, background, size, board)
pygame.time.wait(500)
winner = game.get_winner()
if winner == BLACK:
victory = pygame.image.load('assets/player1_victory.png')
game_surface.blit(victory, (300, 300))
pygame.display.flip()
pygame.time.wait(3000)
return
elif winner == WHITE:
defeat = pygame.image.load('assets/player2_victory.png')
game_surface.blit(defeat, (300, 300))
pygame.display.flip()
pygame.time.wait(3000)
return
else:
draw = pygame.image.load('assets/draw.png')
game_surface.blit(draw, (300, 300))
pygame.display.flip()
pygame.time.wait(3000)
return
def run_game(black: Player,
white: Player,
size: int,
verbose: bool = False) -> tuple[str, list[str]]:
"""Run a Reversi game between the two given players.
Return the winner and list of moves made in the game.
"""
game = ReversiGame(size)
move_sequence = []
previous_move = None
timer = {BLACK: 0, WHITE: 0}
current_player = black
if verbose:
game.print_game()
while game.get_winner() is None:
t0 = time.time() # record time before player make move
previous_move = current_player.make_move(game, previous_move)
t = time.time() # record time after player make move
game.make_move(previous_move)
move_sequence.append(previous_move)
if verbose:
if current_player is black:
print(f'{BLACK} moved {previous_move}. Used {t - t0:.2f}s')
else:
print(f'{WHITE} moved {previous_move}. Used {t - t0:.2f}s')
game.print_game()
if current_player is black:
timer[BLACK] += t - t0
current_player = white
else:
timer[WHITE] += t - t0
current_player = black
# print winner
if verbose:
print(f'Winner: {game.get_winner()}')
print(
f'{BLACK}: {game.get_num_pieces()[BLACK]}, {WHITE}: {game.get_num_pieces()[WHITE]}'
)
print(
f'{BLACK} used {timer[BLACK]:.2f}s, {WHITE} used {timer[WHITE]:.2f}s'
)
return game.get_winner(), move_sequence
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
def heuristic(game: ReversiGame, heuristic_list: list[list[int]]) -> float:
"""
heuristic takes a given heuristic_list and returns the game-state value
given by the list
"""
if game.get_winner() is None:
pieces = game.get_board().pieces
black = 0
white = 0
length = len(pieces)
for i in range(length):
for m in range(length):
if pieces[i][m] == 1:
black += heuristic_list[i][m]
elif pieces[i][m] == -1:
white += heuristic_list[i][m]
return white - black
elif game.get_winner() == 'white':
return 100000
elif game.get_winner() == 'black':
return -100000
else:
return 0
def _value_eval(self, game: ReversiGame, piece: str) -> Union[float, int]:
"""The evaluation function for minimax. For Positional Player, the evaluation function
will evaluate the positional advantage of the pieces on the board.
Preconditions:
- piece in {BLACK, WHITE}
:param game: the current game state for evaluation
:return: value evaluated from the current game state
"""
if game.get_winner() is not None:
if game.get_winner() == piece: # win
return math.inf
elif game.get_winner() == 'Draw': # draw
return 0
else: # lose
return -math.inf
else:
num_black, num_white = game.get_num_pieces(
)[BLACK], game.get_num_pieces()[WHITE]
board_filled = (num_black + num_white) / (game.get_size()**2)
if game.get_size() == 8:
selected_board_weight = BOARD_WEIGHT_8
else:
selected_board_weight = BOARD_WEIGHT_6
if board_filled < 0.80:
return positional_early(game, selected_board_weight, piece)
else:
if piece == BLACK:
return num_black / num_white
if piece == WHITE:
return num_white / num_black
return 0
def _value_eval(self, game: ReversiGame, piece: str) -> Union[float, int]:
"""The evaluation function for minimax. The evaluation function will
return the number of piece of its side
Preconditions:
- piece in {BLACK, WHITE}
:param game: the current game state for evaluation
:return: the evaluated value of the current state
"""
if game.get_winner() is not None:
if game.get_winner() == piece: # win
return math.inf
elif game.get_winner() == 'Draw': # draw
return 0
else: # lose
return -math.inf
else:
if piece == BLACK:
return game.get_num_pieces()[BLACK] / game.get_num_pieces(
)[WHITE]
else:
return game.get_num_pieces()[WHITE] / game.get_num_pieces(
)[BLACK]
def check_same(player1: Player, player2: Player) -> None:
"""
check_same is a function that determines if two players return the same move throughout a game.
this is particularly useful for comparison between MinimaxPlayer and MinimaxABPlayer.
It also gives the time that each player takes to find a move. You must comment out the
random.shuffle() line of code in both players before testing
"""
game = ReversiGame()
prev_move = (-1, -1)
while game.get_winner() is None:
start_time = time.time()
print("Player 1 CHOOSING")
move1 = player1.make_move(game, prev_move)
print("--- %s seconds ---" % (time.time() - start_time))
start_time = time.time()
print("Player 2 CHOOSING")
move2 = player2.make_move(game, prev_move)
print("--- %s seconds ---" % (time.time() - start_time))
print("Player 1 chose: ", move1, " Player 2 chose: ", move2)
assert move1 == move2
game.try_make_move(move1)
prev_move = move1
def build_minimax_tree(self,
game: ReversiGame,
piece: str,
depth: int,
find_max: bool,
previous_move: str,
alpha: float = -math.inf,
beta: float = math.inf) -> MinimaxTree:
"""Construct a tree with a height of depth, prune branches based on the Tree's
evaluate function"""
game_tree = MinimaxTree(move=previous_move,
maximize=find_max,
alpha=alpha,
beta=beta)
if game.get_winner() is not None or depth == 0:
game_tree.eval = self._value_eval(game, piece)
else:
valid_moves = game.get_valid_moves()
random.shuffle(valid_moves)
for move in valid_moves:
game_after_move = game.simulate_move(move)
subtree = self.build_minimax_tree(game_after_move,
piece,
depth - 1,
not find_max,
move,
alpha=game_tree.alpha,
beta=game_tree.beta)
game_tree.add_subtree(subtree)
if game_tree.beta <= game_tree.alpha:
break
return game_tree
# List of moves made
moves_made = [(-1, -1)]
# List of game win results
results = []
# Add UI to the window
ui_handler.add_ui(window, game, results, colour_to_player)
# Window loop
while window.is_running():
""" UPDATE STUFF """
# Get game winner
winner = game.get_winner()
if winner is not None:
results.append(winner)
ui_handler.update_games_stored_text(len(results), window)
increment_player_score(winner, window)
game.start_game(human_player=game.get_human_player())
# If the game is not paused, look for mouse clicks and process moves.
if not ui_handler.get_game_paused():
if game.get_human_player() == game.get_current_player():
# Look at the mouse clicks and see if they are in the board.
for event in window.get_events():
if event[0] == pygame.MOUSEBUTTONUP:
square = board_manager.check_mouse_press(
event[1], game.get_board())
def _run_ai_game(game_surface: pygame.Surface, size: int,
ai_player: Union[MobilityTreePlayer, PositionalTreePlayer, RandomPlayer,
ReversiGame, MCTSTimeSavingPlayer],
user_side: str = BLACK) -> None:
if size == 8:
background = pygame.image.load('assets/gameboard8.png')
elif size == 6:
background = pygame.image.load('assets/gameboard6.png')
else:
raise ValueError("invalid size.")
game_surface.blit(background, (0, 0))
pygame.display.flip()
game = ReversiGame(size)
previous_move = '*'
if user_side == BLACK:
ai_side: str = WHITE
else:
ai_side: str = BLACK
board = game.get_game_board()
_draw_game_state(game_surface, background, size, board)
pass_move = pygame.image.load('assets/pass.png')
while game.get_winner() is None:
if (previous_move == '*' and user_side == WHITE) or game.get_current_player() == user_side:
if game.get_valid_moves() == ['pass']:
game.make_move('pass')
previous_move = 'pass'
surface = game_surface
game_surface.blit(pass_move, (300, 300))
pygame.display.flip()
pygame.time.wait(1000)
game_surface.blit(surface, (0, 0))
pygame.display.flip()
continue
while True:
event = pygame.event.wait()
if event.type == pygame.MOUSEBUTTONDOWN:
mouse_pos = pygame.mouse.get_pos()
if 585 <= mouse_pos[0] <= 795 and 10 <= mouse_pos[1] <= 41:
return
else:
move = _search_for_move(mouse_pos, size)
print(move)
if move == '' or move not in game.get_valid_moves():
continue
else:
previous_move = move
game.make_move(move)
board = game.get_game_board()
_draw_game_state(game_surface, background, size, board)
pygame.time.wait(1000)
break
if event.type == pygame.QUIT:
return
else:
move = ai_player.make_move(game, previous_move)
previous_move = move
game.make_move(move)
if move == 'pass':
surface = game_surface
game_surface.blit(pass_move, (300, 300))
pygame.display.flip()
pygame.time.wait(1000)
game_surface.blit(surface, (0, 0))
pygame.display.flip()
else:
board = game.get_game_board()
_draw_game_state(game_surface, background, size, board)
winner = game.get_winner()
if winner == user_side:
victory = pygame.image.load('assets/victory.png')
game_surface.blit(victory, (300, 300))
pygame.display.flip()
pygame.time.wait(3000)
return
elif winner == ai_side:
defeat = pygame.image.load('assets/defeat.png')
game_surface.blit(defeat, (300, 300))
pygame.display.flip()
pygame.time.wait(3000)
return
else:
draw = pygame.image.load('assets/draw.png')
game_surface.blit(draw, (300, 300))
pygame.display.flip()
pygame.time.wait(3000)
return
