DQN-tensorflow
DQN-tensorflow copied to clipboard
The Gym envirment has bug so the training does't give good reward
The best reward would be 30, that all. But by replacing Gym with ROM directly, the output would be very different, very stable reward around 300~400
I dont' know exactly what's wrong with Gym
Could you explain the steps on replacing Gym with ROM?
I have encountered the same problem that my best reward is only 45 with Gym. If you had find out what's wrong, please let me know. Thanks.
I seem to understand. The new gym environment is different. If you directly use 'Breakout-v0', you will skip four frames in the middle. You should use 'BreakoutNoFrameskip-v0'