hongshaorou/Tianshou
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

self play

Browse Source
This commit is contained in:
rtz19970824 2017-12-08 17:05:33 +08:00
parent b687241a7d
commit 906ced84a3
8 changed files with 182 additions and 104 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
AlphaGo/game.py
View File

@ -190,7 +190,7 @@ class Game:
self.executor = Executor(game=self)
self.history = []
self.past = deque(maxlen=8)
for i in range(8):
for _ in range(8):
self.past.append(self.board)
def _flatten(self, vertex):
@ -205,6 +205,9 @@ class Game:
def clear(self):
self.board = [utils.EMPTY] * (self.size * self.size)
self.history = []
for _ in range(8):
self.past.append(self.board)
def set_size(self, n):
self.size = n
@ -225,7 +228,7 @@ class Game:
def gen_move(self, color):
# move = self.strategy.gen_move(color)
# return move
move = self.strategy.gen_move(self.past, color)
move, self.prob = self.strategy.gen_move(self.past, color)
self.do_move(color, move)
return move

5
AlphaGo/network_small.py
View File

@ -59,11 +59,12 @@ class Network(object):
self.build_network()
def build_network(self):
h = layers.conv2d(self.x, 256, kernel_size=3, stride=1, activation_fn=tf.nn.relu, normalizer_fn=layers.batch_norm,
h = layers.conv2d(self.x, 256, kernel_size=3, stride=1, activation_fn=tf.nn.relu,
normalizer_fn=layers.batch_norm,
normalizer_params={'is_training': self.is_training,
'updates_collections': tf.GraphKeys.UPDATE_OPS},
weights_regularizer=layers.l2_regularizer(1e-4))
for i in range(19):
for i in range(4):
h = residual_block(h, self.is_training)
self.v = value_heads(h, self.is_training)
self.p = policy_heads(h, self.is_training)

82
AlphaGo/self-play.py
View File

@ -1,40 +1,98 @@
from game import Game
from engine import GTPEngine
import re
import numpy as np
from collections import deque
import utils
import argparse
g = Game()
parser = argparse.ArgumentParser()
parser.add_argument('--result_path', type=str, default='./part1')
args = parser.parse_args()
game = Game()
engine = GTPEngine(game_obj=game)
history = deque(maxlen=8)
for i in range(8):
history.append(game.board)
state = []
prob = []
winner = []
pattern = "[A-Z]{1}[0-9]{1}"
game.show_board()
def history2state(history, color):
state = np.zeros([1, game.size, game.size, 17])
for i in range(8):
state[0, :, :, i] = np.array(np.array(history[i]) == np.ones(game.size ** 2)).reshape(game.size, game.size)
state[0, :, :, i + 8] = np.array(np.array(history[i]) == -np.ones(game.size ** 2)).reshape(game.size, game.size)
if color == utils.BLACK:
state[0, :, :, 16] = np.ones([game.size, game.size])
if color == utils.WHITE:
state[0, :, :, 16] = np.zeros([game.size, game.size])
return state
g.show_board()
e = GTPEngine(game_obj=g)
num = 0
game_num = 0
black_pass = False
white_pass = False
while not (black_pass and white_pass):
while True:
while not (black_pass and white_pass) and num < game.size ** 2 * 2:
if num % 2 == 0:
res = e.run_cmd(str(num) + " genmove BLACK")
color = utils.BLACK
new_state = history2state(history, color)
state.append(new_state)
result = engine.run_cmd(str(num) + " genmove BLACK")
num += 1
# print(res)
match = re.search(pattern, res)
match = re.search(pattern, result)
if match is not None:
print(match.group())
else:
print("pass")
if re.search("pass", res) is not None:
if re.search("pass", result) is not None:
black_pass = True
else:
black_pass = False
else:
res = e.run_cmd(str(num) + " genmove WHITE")
color = utils.WHITE
new_state = history2state(history, color)
state.append(new_state)
result = engine.run_cmd(str(num) + " genmove WHITE")
num += 1
match = re.search(pattern, res)
match = re.search(pattern, result)
if match is not None:
print(match.group())
else:
print("pass")
if re.search("pass", res) is not None:
if re.search("pass", result) is not None:
white_pass = True
else:
white_pass = False
g.show_board()
game.show_board()
prob.append(np.array(game.prob).reshape(-1, game.size ** 2 + 1))
print("Finished")
score = game.executor.get_score()
if score > 0:
winner = utils.BLACK
else:
winner = utils.WHITE
state = np.concatenate(state, axis=0)
prob = np.concatenate(prob, axis=0)
winner = np.ones([num, 1]) * winner
assert state.shape[0] == prob.shape[0]
assert state.shape[0] == winner.shape[0]
np.savez(args.result_path + "/game" + game_num, state=state, prob=prob, winner=winner)
state = []
prob = []
winner = []
num = 0
black_pass = False
white_pass = False
engine.run_cmd(str(num) + " clear_board")
history.clear()
for _ in range(8):
history.append(game.board)
game.show_board()
game_num += 1

45
AlphaGo/strategy.py
View File

@ -198,28 +198,27 @@ class GoEnv:
id_ = self._flatten(vertex)
if self.board[id_] == utils.EMPTY:
self.board[id_] = color
self.history.append(copy.copy(self.board))
return True
else:
return False
def step_forward(self, state, action):
if state[0, 0, 0, -1] == 1:
color = 1
color = utils.BLACK
else:
color = -1
if action == 81:
vertex = (0, 0)
color = utils.WHITE
if action == self.size ** 2:
vertex = utils.PASS
else:
vertex = (action % 9 + 1, action / 9 + 1)
vertex = (action % self.size + 1, action / self.size + 1)
# print(vertex)
# print(self.board)
self.board = (state[:, :, :, 7] - state[:, :, :, 15]).reshape(-1).tolist()
self.do_move(color, vertex)
new_state = np.concatenate(
[state[:, :, :, 1:8], (np.array(self.board) == 1).reshape(1, 9, 9, 1),
state[:, :, :, 9:16], (np.array(self.board) == -1).reshape(1, 9, 9, 1),
np.array(1 - state[:, :, :, -1]).reshape(1, 9, 9, 1)],
[state[:, :, :, 1:8], (np.array(self.board) == utils.BLACK).reshape(1, self.size, self.size, 1),
state[:, :, :, 9:16], (np.array(self.board) == utils.WHITE).reshape(1, self.size, self.size, 1),
np.array(1 - state[:, :, :, -1]).reshape(1, self.size, self.size, 1)],
axis=3)
return new_state, 0
@ -233,26 +232,26 @@ class strategy(object):
feed_dict={self.net.x: state, self.net.is_training: False})
def data_process(self, history, color):
state = np.zeros([1, 9, 9, 17])
state = np.zeros([1, self.simulator.size, self.simulator.size, 17])
for i in range(8):
state[0, :, :, i] = np.array(np.array(history[i]) == np.ones(81)).reshape(9, 9)
state[0, :, :, i + 8] = np.array(np.array(history[i]) == -np.ones(81)).reshape(9, 9)
if color == 1:
state[0, :, :, 16] = np.ones([9, 9])
if color == -1:
state[0, :, :, 16] = np.zeros([9, 9])
state[0, :, :, i] = np.array(np.array(history[i]) == np.ones(self.simulator.size ** 2)).reshape(self.simulator.size, self.simulator.size)
state[0, :, :, i + 8] = np.array(np.array(history[i]) == -np.ones(self.simulator.size ** 2)).reshape(self.simulator.size, self.simulator.size)
if color == utils.BLACK:
state[0, :, :, 16] = np.ones([self.simulator.size, self.simulator.size])
if color == utils.WHITE:
state[0, :, :, 16] = np.zeros([self.simulator.size, self.simulator.size])
return state
def gen_move(self, history, color):
self.simulator.history = copy.copy(history)
self.simulator.board = copy.copy(history[-1])
state = self.data_process(self.simulator.history, color)
mcts = MCTS(self.simulator, self.evaluator, state, 82, inverse=True, max_step=10)
mcts = MCTS(self.simulator, self.evaluator, state, self.simulator.size ** 2 + 1, inverse=True, max_step=100)
temp = 1
p = mcts.root.N ** temp / np.sum(mcts.root.N ** temp)
choice = np.random.choice(82, 1, p=p).tolist()[0]
if choice == 81:
move = (0, 0)
prob = mcts.root.N ** temp / np.sum(mcts.root.N ** temp)
choice = np.random.choice(self.simulator.size ** 2 + 1, 1, p=prob).tolist()[0]
if choice == self.simulator.size ** 2:
move = utils.PASS
else:
move = (choice % 9 + 1, choice / 9 + 1)
return move
move = (choice % self.simulator.size + 1, choice / self.simulator.size + 1)
return move, prob

14
AlphaGo/test.py Normal file
View File

@ -0,0 +1,14 @@
import sys
from game import Game
from engine import GTPEngine
# import utils
game = Game()
engine = GTPEngine(game_obj=game, name='tianshou')
cmd = raw_input
while not engine.disconnect:
command = cmd()
result = engine.run_cmd(command)
sys.stdout.write(result)
sys.stdout.flush()

1
bin/activate Symbolic link
View File

@ -0,0 +1 @@
/home/tongzheng/anaconda2/bin/activate

1
bin/conda Symbolic link
View File

@ -0,0 +1 @@
/home/tongzheng/anaconda2/bin/conda

1
bin/deactivate Symbolic link
View File

@ -0,0 +1 @@
/home/tongzheng/anaconda2/bin/deactivate