class ConnectFourBotNN(gym.Env):
"""
Description:
ConnectFour game bot
"""
def __init__(self, w, b):
self.board = ConnectFourEnv()
self.NN = Linear(w, b)
def nextMove(self):
boardvalues = self.board.board.flatten()
mytensor = tf.constant(boardvalues, dtype='float32')
x = self.NN([mytensor])
available_moves = self.board.available_moves()
for i in reversed(argsort(x)):
for j in i:
for s in available_moves:
if j == s:
return j
def inform(self, action):
self.board.step(action)
def reset(self):
self.board = ConnectFourEnv()
class ConnectFourBotRandom(gym.Env):
"""
Description:
ConnectFour game bot
"""
def __init__(self):
self.board = ConnectFourEnv()
def nextMove(self):
x = list(self.board.available_moves())
shuffle(x)
return x[0]
def inform(self, action):
self.board.step(action)
def reset(self):
self.board = ConnectFourEnv()
b_init = tf.zeros_initializer()
b = tf.Variable(initial_value=b_init(shape=(7, ), dtype='float32'),
trainable=True)
bot2 = ConnectFourBotRandom()
bot1 = ConnectFourBotNN(w, b)
numberiter = 2
number_ga_configs = 2
results_log = np.array([])
gameswon = 0
gamesundecided = 0
maximum = np.array([])
for x in range(number_ga_configs):
for x in range(numberiter):
board = ConnectFourEnv()
bot1.reset()
bot2.reset()
current_player = 1
while not (board.is_win_state()):
if current_player == 1:
move = bot1.nextMove()
else:
move = bot2.nextMove()
current_player *= -1
if board.is_valid_action(move):
board.step(move)
bot1.inform(move)
bot2.inform(move)
if len(board.available_moves()) == 0:
break
def reset(self):
self.board = ConnectFourEnv()
def __init__(self, w, b):
self.board = ConnectFourEnv()
self.NN = Linear(w, b)
def __init__(self):
self.board = ConnectFourEnv()
def test_available_moves():
env = ConnectFourEnv()
env.reset(BOARD_AVAILABLE_0123)
assert set(env.available_moves()) == {0, 1, 2, 3}
env.reset(BOARD_AVAILABLE_2)
assert set(env.available_moves()) == {2}
env.reset(BOARD_AVAILABLE_6)
assert set(env.available_moves()) == {6}
env.reset(BOARD_AVAILABLE_NONE)
assert set(env.available_moves()) == set([])
def test_is_win_state():
env = ConnectFourEnv()
env.reset(BOARD_WIN_ROW)
assert env.is_win_state()
env.reset(BOARD_WIN_COLUMN)
assert env.is_win_state()
env.reset(BOARD_WIN_DIAGONAL)
assert env.is_win_state()
env.reset(BOARD_WIN_BDIAGONAL)
assert env.is_win_state()
def test_is_valid_action():
env = ConnectFourEnv()
env.reset(BOARD_VALIDATION)
assert env.is_valid_action(0)
assert not env.is_valid_action(3)