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

fix bug in check_global_isomorphous and refactor _is_suicide again

Browse Source
This commit is contained in:
Dong Yan 2017-12-19 12:00:17 +08:00
parent 99a617a1f0
commit 4440294c12
1 changed files with 14 additions and 18 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

32
AlphaGo/strategy.py
View File

@ -42,33 +42,27 @@ class GoEnv:
return has_liberty, chain return has_liberty, chain
def _is_suicide(self, color, vertex): def _is_suicide(self, color, vertex):
### assume that we already take this move self.simulate_board[self.simulate_flatten(vertex)] = color # assume that we already take this move
self.simulate_board[self.simulate_flatten(vertex)] = color suicide = False
has_liberty, group = self._find_group(vertex) has_liberty, group = self._find_group(vertex)
if has_liberty: if not has_liberty:
### this group still has liberty after this move, not suicide suicide = True # no liberty, suicide
self.simulate_board[self.simulate_flatten(vertex)] = utils.EMPTY
return False
else:
### liberty is zero
for n in self._neighbor(vertex): for n in self._neighbor(vertex):
if self.simulate_board[self.simulate_flatten(n)] == utils.another_color(color): if self.simulate_board[self.simulate_flatten(n)] == utils.another_color(color):
opponent_liberty, group = self._find_group(n) opponent_liberty, group = self._find_group(n)
# this move is able to take opponent's stone, not suicide
if not opponent_liberty: if not opponent_liberty:
self.simulate_board[self.simulate_flatten(vertex)] = utils.EMPTY suicide = False # this move is able to take opponent's stone, not suicide
return False
# not a take, suicide self.simulate_board[self.simulate_flatten(vertex)] = utils.EMPTY # undo this move
self.simulate_board[self.simulate_flatten(vertex)] = utils.EMPTY return suicide
return True
def _check_global_isomorphous(self, color, vertex): def _check_global_isomorphous(self, color, vertex):
##backup ##backup
_board = copy.copy(self.simulate_board) _board = copy.copy(self.simulate_board)
self.simulate_board[self.simulate_flatten(vertex)] = color self.simulate_board[self.simulate_flatten(vertex)] = color
self._process_board(color, vertex) self._process_board(color, vertex)
if self.simulate_board in self.simulate_latest_boards: if self.simulate_board in self.game.history:
res = True res = True
else: else:
res = False res = False
@ -140,7 +134,9 @@ class GoEnv:
return True return True
def simulate_is_valid(self, state, action): def simulate_is_valid(self, state, action):
# state is the play board, the shape is [1, 9, 9, 17] # 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 action == self.game.size ** 2: if action == self.game.size ** 2:
vertex = (0, 0) vertex = (0, 0)
else: else:
@ -177,7 +173,7 @@ class GoEnv:
return True return True
def do_move(self, color, vertex): def simulate_do_move(self, color, vertex):
if vertex == utils.PASS: if vertex == utils.PASS:
return True return True
@ -200,7 +196,7 @@ class GoEnv:
# print(vertex) # print(vertex)
# print(self.board) # print(self.board)
self.simulate_board = (state[:, :, :, 7] - state[:, :, :, 15]).reshape(-1).tolist() self.simulate_board = (state[:, :, :, 7] - state[:, :, :, 15]).reshape(-1).tolist()
self.do_move(color, vertex) self.simulate_do_move(color, vertex)
new_state = np.concatenate( new_state = np.concatenate(
[state[:, :, :, 1:8], (np.array(self.simulate_board) == utils.BLACK).reshape(1, self.game.size, self.game.size, 1), [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), state[:, :, :, 9:16], (np.array(self.simulate_board) == utils.WHITE).reshape(1, self.game.size, self.game.size, 1),