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

repair komi. add todo for forbid pass:

Browse Source
This commit is contained in:
Wenbo Hu 2017-12-20 22:57:58 +08:00
parent 40909fa994
commit 336cede197
3 changed files with 4 additions and 7 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 return 'unknown player', False
def cmd_get_score(self, args, **kwargs): def cmd_get_score(self, args, **kwargs):
return self._game.game_engine.executor_get_score(), None return self._game.game_engine.executor_get_score(True), None
def cmd_show_board(self, args, **kwargs): def cmd_show_board(self, args, **kwargs):
return self._game.board, True return self._game.board, True

4
AlphaGo/game.py
View File

@ -23,7 +23,7 @@ class Game:
TODO : Maybe merge with the engine class in future, TODO : Maybe merge with the engine class in future,
currently leave it untouched for interacting with Go UI. currently leave it untouched for interacting with Go UI.
''' '''
def __init__(self, size=9, komi=6.5, checkpoint_path=None): def __init__(self, size=9, komi=3.75, checkpoint_path=None):
self.size = size self.size = size
self.komi = komi self.komi = komi
self.board = [utils.EMPTY] * (self.size ** 2) self.board = [utils.EMPTY] * (self.size ** 2)
@ -75,7 +75,7 @@ class Game:
self.game_engine.simulate_board = copy.copy(latest_boards[-1]) self.game_engine.simulate_board = copy.copy(latest_boards[-1])
nn_input = self.generate_nn_input(self.game_engine.simulate_latest_boards, color) nn_input = self.generate_nn_input(self.game_engine.simulate_latest_boards, color)
mcts = MCTS(self.game_engine, self.evaluator, [self.game_engine.simulate_latest_boards, color], self.size ** 2 + 1, inverse=True) mcts = MCTS(self.game_engine, self.evaluator, [self.game_engine.simulate_latest_boards, color], self.size ** 2 + 1, inverse=True)
mcts.search(max_step=1) mcts.search(max_step=5)
temp = 1 temp = 1
prob = mcts.root.N ** temp / np.sum(mcts.root.N ** temp) prob = mcts.root.N ** temp / np.sum(mcts.root.N ** temp)
choice = np.random.choice(self.size ** 2 + 1, 1, p=prob).tolist()[0] choice = np.random.choice(self.size ** 2 + 1, 1, p=prob).tolist()[0]

5
AlphaGo/go.py
View File

@ -121,12 +121,8 @@ class Go:
if self._is_eye(current_board, color, vertex): if self._is_eye(current_board, color, vertex):
return False return False
# forbid position on its own eye. # forbid position on its own eye.
#if self._is_game_finish(current_board, color) and vertex == utils.PASS
# return False
# forbid pass if the game is not finished.
return True return True
def _is_game_finished(self, current_board, color): def _is_game_finished(self, current_board, color):
''' '''
for each empty position, if it has both BLACK and WHITE neighbors, the game is still not finished for each empty position, if it has both BLACK and WHITE neighbors, the game is still not finished
@ -192,6 +188,7 @@ class Go:
if len(invalid_action_list) < len(action_set) - 1: if len(invalid_action_list) < len(action_set) - 1:
invalid_action_list.append(action_set[-1]) invalid_action_list.append(action_set[-1])
# forbid pass, if we have other choices # forbid pass, if we have other choices
# TODO: In fact we should not do this. In some extreme cases, we should permit pass.
return invalid_action_list return invalid_action_list
def _do_move(self, board, color, vertex): def _do_move(self, board, color, vertex):