def test_get_move(self):
board = TTTBoard(TestTTTBoard.blank_board)
player1 = RandomPlayer(1, seed=42)
player2 = RandomPlayer(1, seed=42)
a = player1.get_move(board)
b = player2.get_move(board)
self.assertEqual(a.board, b.board)
a = player2.get_move(board)
b = player1.get_move(board)
self.assertEqual(a.board, b.board)
def get_move(self, board):
moves = board.available_moves()
if moves:
for move in moves:
if THandPlayer.next_move_winner(board, move, self.mark):
return move
elif THandPlayer.next_move_winner(board, move,
self.opponent_mark):
return move
else:
return RandomPlayer.get_move(board)
def get_move(self, board):
if np.random.uniform(
) < self.epsilon: # With probability epsilon, choose a move at random ("epsilon-greedy" exploration)
return RandomPlayer.get_move(board)
else:
state_key = QPlayer.make_and_maybe_add_key(board, self.mark,
self.Q)
print state_key
Qs = self.Q[state_key]
print Qs
if self.mark == "X":
print QPlayer.stochastic_argminmax(Qs, max)
return QPlayer.stochastic_argminmax(Qs, max)
elif self.mark == "O":
print QPlayer.stochastic_argminmax(Qs, min)
return QPlayer.stochastic_argminmax(Qs, min)