class ComputerPlayer(object):
# Loss, Tie, Win
rewards = [50, 400, 900]
table = None
def __init__(self, game, player):
self.player = player
self.agent = Agent("tictactoe")
self.game = game
def generate(self):
"Generate a move for the computer player."
msg = sum(x << (n*2) for n, x in enumerate(self.game.board))
msg |= self.player << 18
message = msg
for n in count(1):
action = self.agent.process(message)
pos = action % 9
if self.game.board[pos]:
self.game.output("%d round%s", n, s(n))
self.game.goto(*self.game.square[pos])
self.game.win.refresh()
# Keep part of the failure around.
message = ((action << 20) & 0xFFFF0000) | msg
else:
break
return pos
def result(self, points):
bonus = self.rewards[points + 1]
self.agent.reward(bonus)
def __init__(self, game, player):
self.player = player
self.agent = Agent("tictactoe")
self.game = game
