Closed ethancaballero closed 7 years ago
Just get rid of extra data to speed things up as nothing valuable is learned from agent during transition from life to life. Helps for a few games, mostly for games that time is a factor
Did it help for Breakout?
no it shouldn't as agent needs to learn to fire once new life starts
SpaceInvaders it helps a lot. BeamRider I think it helped too. But any game where agent has to learn to start game up again after lost of life its gonna be detrimental
This is done in Deepminds Alewrap as well as you can see in code here https://github.com/deepmind/alewrap/blob/master/alewrap/GameEnvironment.lua
Does args.count_lives help Seaquest-v0? How do you get the pre-trained Seaquest-v0 model?
run python main.py --env Seaquest-v0 --workers 32
for 3 days?
Why is this in train.py ?