jabberwockyll / deep_rl_ale Goto Github PK

First off, thanks for sharing this awesome repo. I am attempting to reproduce the deepmind results with TF and am slowly getting better results as I buff out the many subtle issues. Your repo has really helped me figure things out!

I wanted to know what results you get for space invaders (on a public post I saw you mentioned 1500), and exactly what args you are using. If haven't run deep_rl_ale for the full 200 epochs but at about 125 (with all default args) I was seeing average scores of about 1000-1100. Maybe I just need to let it run, but I wanted to make sure.

Thanks much!

Hi, what is the running time for each game with single GPU?

Hi,

Thanks for a great library!

Could you explain what line 39 of experiments.py should be doing?
agent.test_state = list(next(zip(*reset)))
If I am not mistaken, reset is a list of states where each state is (s, action, reward, terminal) and line 39 is helping the while loop iterate over this list of lists.

Thanks!