def train_alphazero(lr, dropout, num_channels, epochs, batch_size,
replay_buffer_size, temp_decrese_moves, mcts_rollouts,
n_episodes_per_iteration, eval, model, test):
board = Game(player_turn=1)
network = NeuralNet(board, num_channels, lr, dropout, epochs, batch_size)
if model is not None:
print("Loading {}".format(model))
network.load(model)
if test:
while True:
while board.turn_player() == -1:
move = np.argmax(network(board, board.valid_moves())[0][0])
print("Board {}, move {}".format(board.board(), move))
board.move(move)
print("{}".format(board.board()))
import pdb
pdb.set_trace()
# set up the experiment
experiment = Experiment(
api_key=os.environ.get('ALPHAZERO_API_KEY'),
project_name=os.environ.get('ALPHAZERO_PROJECT_NAME'),
workspace=os.environ.get('ALPHAZERO_WORKSPACE'))
experiment.log_multiple_params({
'lr':
lr,
'dropout':
dropout,
'num_channels':
num_channels,
'epochs':
epochs,
'batch_size':
batch_size,
'replay_buffer_size':
replay_buffer_size,
'temp_decrese_moves':
temp_decrese_moves,
'mcts_rollouts':
mcts_rollouts,
'n_episodes_per_iteration':
n_episodes_per_iteration
})
buf = ReplayBuffer(replay_buffer_size, batch_size)
epoch = 0
while True:
epoch += 1
print("Epoch {}, {}".format(epoch, time.clock()))
for i in range(n_episodes_per_iteration):
winner = execute_episode(network, buf, experiment)
print("Finished episode {}, winner {}, time {}".format(
i, winner, time.clock()))
network.clone()
loss, entropy = train_network(network, buf, experiment)
print("Training loss: {}, entropy: {}".format(loss, entropy))
won_counter = evaluate_network(network, board, 10)
if won_counter >= 5:
print("Performance improved, {} games won".format(won_counter))
network.save()
else:
print("Performance decreased, {} games won".format(won_counter))
network.revert_network()
