boubnanm / deep-reinforcement-learning-applied-to-doom Goto Github PK

I try to train DQN with your code of the basic scenario,and I set the total_episodes to 1000.However,the agent looks like it can't find the target and shoot.Is the due to the flaw of DQN?

Hi, Swirler. Do you have some ideas about how to generate mazes in doom by ourselves?

Actually, I could build a wad file about maze with omgifol module. Unfortunately, I don't know how to set a goal in maze. Would you please do me a favour?

Waiting for your reply. Thank you very very much.

Hi, How do you think about reward smoothing.
The collected rewards have high variance. In order to show the tendency of reward curve, should we do some reward smoothing operation as same as tensorboard smoothing?
If so, which smoothing method should I choose, exponential smoothing or average smoothing?

Hi, it seems that in this code the agent cannot learn to navigation in my_way_home, does it?