def nn_vs_nn_export_better_player():
player1 = NNAgent1(verbose = True)
player2 = NNAgent1(load_best=True)
stats = Statistic(player1, verbose=True)
while True:
bg = Backgammon()
bg.set_player_1(player1)
bg.set_player_2(player2)
winner = bg.play()
player1.add_reward(winner)
player2.add_reward(-1 * winner)
stats.add_win(winner)
if stats.nn_is_better() and stats.games_played % 100 == 0:
break
# only way to reach this point is if the current
# neural network is better than the BestNNAgent()
# ... at least I think so
# thus, we export the current as best
print("Congratulations, you brought the network one step closer")
print("to taking over the world (of backgammon)!!!")
player1.export_model(filename="nn_best_model")
def do_default():
"""
Play with a neural network against random
"""
player1 = get_agent_by_config_name('nn_pg_2', 'best')
player2 = get_agent_by_config_name('random', 'None')
player1.training = True
player2.training = True
stats = Statistic(player1, verbose=True)
# play games forever
while True:
bg = Backgammon()
bg.set_player_1(player1)
bg.set_player_2(player2)
winner = bg.play()
player1.add_reward(winner)
player2.add_reward(-winner)
# Reward the neural network agent
# player1.reward_player(winner)
stats.add_win(winner)
def train(competitors):
# Train
print("Training...")
iteration = 0
while True:
iteration += 1
competitor1, competitor2 = random_pair_not_self(competitors)
player1 = competitor1['agent']
player2 = competitor2['agent']
player1.training = True
player2.training = True
bg = Backgammon()
bg.set_player_1(player1)
bg.set_player_2(player2)
# 1 if player 1 won, -1 if player 2 won
result = bg.play()
player1.add_reward(result)
player2.add_reward(-result)
update_wins_and_losses(result, competitor1, competitor2)
# Rate performance
competitor1['rating'], competitor2['rating'] = update_rating(
competitor1['rating'], competitor2['rating'], result)
if iteration % 10 == 0:
print_competitors(competitors, iteration)
if iteration % (100 * len(competitors)) == 0:
save_competitors(competitors)
def plan(self, board):
time_when_planning_should_stop = time.time() * 1000 + 250
model_agent, transient_agent = self.initialize_planning_phase()
while time.time() * 1000 < time_when_planning_should_stop:
copy_of_board = copy.deepcopy(board)
game = Backgammon()
game.reset()
game.set_player_1(model_agent)
game.set_player_2(transient_agent)
reward = game.play(start_with_this_board=copy_of_board)
transient_agent.add_reward(reward)
def self_play():
"""
Makes a human agent play against another (or the same) human agent.
"""
player1 = HumanAgent()
player2 = HumanAgent()
bg = Backgammon()
bg.set_player_1(player1)
bg.set_player_2(player2)
bg.play()
def test_play():
"""
Makes a human agent play against another (or the same) human agent.
"""
player1 = HumanAgent()
player2 = get_agent_by_config_name('nn_pg', 'best')
bg = Backgammon()
bg.set_player_1(player1)
bg.set_player_2(player2)
bg.play()
def random_play():
"""
Makes a random agent play against another random agent.
"""
player1 = RandomAgent()
player2 = RandomAgent()
bg = Backgammon()
bg.set_player_1(player1)
bg.set_player_2(player2)
bg.play(commentary=True, verbose=True)