Merge pull request #2 from tsu-nera/master
Add diagonals in game over conditions
This commit is contained in:
commit
e8dcc0fb4f
@ -39,6 +39,11 @@ class TicTacToeEnv(gym.Env):
|
|||||||
reward = p
|
reward = p
|
||||||
done = True
|
done = True
|
||||||
break
|
break
|
||||||
|
# diagonals
|
||||||
|
if((board[0] == p and board[4] == p and board[8] == p)
|
||||||
|
or (board[2] == p and board[4] == p and board[6] == p)):
|
||||||
|
reward = p
|
||||||
|
done = True
|
||||||
|
|
||||||
return self.state, reward, done, {}
|
return self.state, reward, done, {}
|
||||||
def _reset(self):
|
def _reset(self):
|
||||||
|
Loading…
Reference in New Issue
Block a user