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

final version before merge Go and GoEnv

Browse Source
This commit is contained in:
Dong Yan 2017-12-20 00:43:31 +08:00
parent 2a9d949510
commit d1af137686
5 changed files with 29 additions and 24 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
AlphaGo/engine.py
View File

@ -183,7 +183,7 @@ class GTPEngine():
return 'unknown player', False
def cmd_get_score(self, args, **kwargs):
return self._game.executor.get_score(), None
return self._game.executor.executor_get_score(), None
def cmd_show_board(self, args, **kwargs):
return self._game.board, True

3
AlphaGo/game.py
View File

@ -78,6 +78,7 @@ class Game:
return state
def think(self, latest_boards, color):
# TODO : using copy is right, or should we change to deepcopy?
self.simulator.simulate_latest_boards = copy.copy(latest_boards)
self.simulator.simulate_board = copy.copy(latest_boards[-1])
nn_input = self.generate_nn_input(self.simulator.simulate_latest_boards, color)
@ -95,7 +96,7 @@ class Game:
# this function can be called directly to play the opponent's move
if vertex == utils.PASS:
return True
res = self.executor.do_move(color, vertex)
res = self.executor.executor_do_move(color, vertex)
return res
def think_play_move(self, color):

8
AlphaGo/go.py
View File

@ -84,7 +84,7 @@ class Go:
repeat = True
return repeat
def is_valid(self, history_boards, current_board, color, vertex):
def _is_valid(self, history_boards, current_board, color, vertex):
### in board
if not self._in_board(vertex):
return False
@ -102,8 +102,8 @@ class Go:
return True
def do_move(self, color, vertex):
if not self.is_valid(self.game.history, self.game.board, color, vertex):
def executor_do_move(self, color, vertex):
if not self._is_valid(self.game.history, self.game.board, color, vertex):
return False
self.game.board[self.game._flatten(vertex)] = color
self._process_board(self.game.board, color, vertex)
@ -164,7 +164,7 @@ class Go:
elif color_estimate < 0:
return utils.WHITE
def get_score(self, is_unknown_estimation = False):
def executor_get_score(self, is_unknown_estimation = False):
'''
is_unknown_estimation: whether use nearby stone to predict the unknown
return score from BLACK perspective.

2
AlphaGo/self-play.py
View File

@ -79,7 +79,7 @@ while True:
prob.append(np.array(game.prob).reshape(-1, game.size ** 2 + 1))
print("Finished")
print("\n")
score = game.executor.get_score(True)
score = game.executor.executor_get_score(True)
if score > 0:
winner = utils.BLACK
else:

38
AlphaGo/strategy.py
View File

@ -117,14 +117,14 @@ class GoEnv:
# print "many opponents, fake eye"
return False
def knowledge_prunning(self, current_board, color, vertex):
def _knowledge_prunning(self, current_board, color, vertex):
### check if it is an eye of yourself
### assumptions : notice that this judgement requires that the state is an endgame
if self._is_eye(current_board, color, vertex):
return False
return True
def sa2cv(self, state, action):
def _sa2cv(self, state, action):
# State is the play board, the shape is [1, self.game.size, self.game.size, 17], action is an index.
# We need to transfer the (state, action) pair into (color, vertex) pair to simulate the move
if state[0, 0, 0, -1] == utils.BLACK:
@ -137,23 +137,13 @@ class GoEnv:
vertex = self.game._deflatten(action)
return color, vertex
def simulate_is_valid(self, history_boards, current_board, state, action):
# initialize simulate_latest_boards and simulate_board from state
self.simulate_latest_boards.clear()
for i in range(8):
self.simulate_latest_boards.append((state[:, :, :, i] - state[:, :, :, i + 8]).reshape(-1).tolist())
self.simulate_board = copy.copy(self.simulate_latest_boards[-1])
color, vertex = self.sa2cv(state, action)
def _is_valid(self, history_boards, current_board, color, vertex):
### in board
if not self._in_board(vertex):
return False
### already have stone
if not current_board[self.game._flatten(vertex)] == utils.EMPTY:
# print(np.array(self.board).reshape(9, 9))
# print(vertex)
return False
### check if it is suicide
@ -164,12 +154,26 @@ class GoEnv:
if self._check_global_isomorphous(history_boards, current_board, color, vertex):
return False
if not self.knowledge_prunning(current_board, color, vertex):
return True
def simulate_is_valid(self, history_boards, current_board, state, action):
# initialize simulate_latest_boards and simulate_board from state
self.simulate_latest_boards.clear()
for i in range(8):
self.simulate_latest_boards.append((state[:, :, :, i] - state[:, :, :, i + 8]).reshape(-1).tolist())
self.simulate_board = copy.copy(self.simulate_latest_boards[-1])
color, vertex = self._sa2cv(state, action)
if not self._is_valid(history_boards, current_board, color, vertex):
return False
if not self._knowledge_prunning(current_board, color, vertex):
return False
return True
def simulate_do_move(self, color, vertex):
def _do_move(self, color, vertex):
if vertex == utils.PASS:
return True
@ -184,9 +188,9 @@ class GoEnv:
# initialize the simulate_board from state
self.simulate_board = (state[:, :, :, 7] - state[:, :, :, 15]).reshape(-1).tolist()
color, vertex = self.sa2cv(state, action)
color, vertex = self._sa2cv(state, action)
self.simulate_do_move(color, vertex)
self._do_move(color, vertex)
new_state = np.concatenate(
[state[:, :, :, 1:8], (np.array(self.simulate_board) == utils.BLACK).reshape(1, self.game.size, self.game.size, 1),
state[:, :, :, 9:16], (np.array(self.simulate_board) == utils.WHITE).reshape(1, self.game.size, self.game.size, 1),