Merge pull request #2 from tsu-nera/master

Add diagonals in game over conditions

gym_tic_tac_toe/envs/tic_tac_toe_env.py

@@ -39,6 +39,11 @@ class TicTacToeEnv(gym.Env):
                 reward = p
                 done = True
                 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, {}
     def _reset(self):