Lections/gym-tic-tac-toe
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

increase penalty for illegal moves

Browse Source
This commit is contained in:
Nicolai Czempin 2017-04-04 17:35:11 +02:00
parent 46f077ef1f
commit 17b9bb7486
1 changed files with 2 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
gym_tic_tac_toe/envs/tic_tac_toe_env.py
View File

@ -22,11 +22,11 @@ class TicTacToeEnv(gym.Env):
if (proposed != 0): # wrong player, not empty if (proposed != 0): # wrong player, not empty
print("illegal move ", action, ". (square occupied): ", square) print("illegal move ", action, ". (square occupied): ", square)
done = True done = True
reward = -om # player who did NOT make the illegal move reward = -2 * om # player who did NOT make the illegal move
if (p != om): # wrong player, not empty if (p != om): # wrong player, not empty
print("illegal move ", action, " not on move: ", p) print("illegal move ", action, " not on move: ", p)
done = True done = True
reward = -om # player who did NOT make the illegal move reward = -2 * om # player who did NOT make the illegal move
else: else:
self.state['board'][square] = p self.state['board'][square] = p
self.state['on_move'] = -p self.state['on_move'] = -p
@ -57,8 +57,6 @@ class TicTacToeEnv(gym.Env):
for i in range (9): for i in range (9):
if (self.state.state['board'][i]== 0): if (self.state.state['board'][i]== 0):
p = self.state.on_move p = self.state.on_move
if (p == 2):
p = -1
m = [p, i] m = [p, i]
moves.append(m) moves.append(m)