def random_v_random(n=1):
"""
Plays two random players against each other
"""
p1_strategy = strategies.RandomStrategy()
p2_strategy = strategies.RandomStrategy()
p1 = player.Player('X', p1_strategy)
p2 = player.Player('O', p2_strategy)
board = tictactoe.Board()
game = rl_game.Game(p1, p2, board)
game.play_one()
def random_v_q(n=1000):
"""
Trains the RL agent against random
"""
for i in range(5):
p1_strategy = strategies.RandomStrategy()
p2_strategy = strategies.QStrategy('O')
p1 = player.Player('X', p1_strategy)
p2 = player.Player('O', p2_strategy)
board = tictactoe.Board()
game = rl_game.Game(p1, p2, board)
game.play_many(n)
def q_v_q():
"""
Plays two Q-strategy players against each other
"""
p1_strategy = strategies.QStrategy('X')
p2_strategy = strategies.QStrategy('O')
p1 = player.Player('X', p1_strategy)
p2 = player.Player('O', p2_strategy)
board = tictactoe.Board()
game = rl_game.Game(p1, p2, board)
game.play_one()
p1.strategy.save_q()
p2.strategy.save_q()
def train_q(n=1000):
"""
Trains the RL agent
"""
for i in range(50):
p1_strategy = strategies.QStrategy('X')
p2_strategy = strategies.QStrategy('O')
p1 = player.Player('X', p1_strategy)
p2 = player.Player('O', p2_strategy)
board = tictactoe.Board()
game = rl_game.Game(p1, p2, board)
game.play_many(n)
p1.strategy.save_q()
p2.strategy.save_q()
def human_v_q(human_player=1):
"""
Allows human to play versus q-learning agent
"""
if human_player == 1:
p1_strategy = strategies.Human()
p2_strategy = strategies.QStrategy('O')
else:
human_player = 2
p1_strategy = strategies.QStrategy('X')
p2_strategy = strategies.Human()
p1 = player.Player('X', p1_strategy)
p2 = player.Player('O', p2_strategy)
board = tictactoe.Board()
message = 'Welcome to tic tac toe!\n'+\
'You are playing against a random opponent and you are player '+str(human_player)+'.\n'+\
'To make a move, enter the number of the square which you would like to play, labelled as:\n'+\
'1, 2, 3\n4, 5, 6\n7, 8, 9\n\n'
print(message)
game = rl_game.Game(p1, p2, board)
game.play_one()