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

simulator process a valid set, instead of a single action

Browse Source
This commit is contained in:
Wenbo Hu 2017-12-20 21:35:35 +08:00
parent 12f45d9dc6
commit 818da800e2
2 changed files with 17 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
AlphaGo/go.py
View File

@ -121,8 +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 #if self._is_game_finish(current_board, color) and vertex == utils.PASS
return False # return False
# forbid pass if the game is not finished. # forbid pass if the game is not finished.
return True return True
@ -183,6 +183,18 @@ class Go:
return True return True
def simulate_is_valid_list(self, state, action_set):
## find all the valid actions
## if no action is valid, then pass
valid_action_set = []
for action_candidate in action_set:
if self.simulate_is_valid(self, state, action_candidate)
valid_action_set.append(action_candidate)
if not valid_action_set:
valid_action_set.append(utils.PASS)
# if valid_action_set is a empty set, add pass
return valid_action_set
def _do_move(self, board, color, vertex): def _do_move(self, board, color, vertex):
if vertex == utils.PASS: if vertex == utils.PASS:
return board return board

7
tianshou/core/mcts/mcts.py
View File

@ -72,12 +72,7 @@ class UCTNode(MCTSNode):
def valid_mask(self, simulator): def valid_mask(self, simulator):
if self.mask is None: if self.mask is None:
self.mask = [] self.mask = simulator.simulate_is_valid_list(self.state, range(self.action_num - 1))
for act in range(self.action_num - 1):
if not simulator.simulate_is_valid(self.state, act):
self.mask.append(act)
self.ucb[act] = -float("Inf")
else:
self.ucb[self.mask] = -float("Inf") self.ucb[self.mask] = -float("Inf")