Training speed (in hours)

miyosuda / async_deep_reinforce

Asynchronous Methods for Deep Reinforcement Learning

Apache License 2.0

592 stars 192 forks source link

Training speed (in hours) #29

Open tgangwani opened 7 years ago

tgangwani commented 7 years ago

I am trying to get a sense of the time the implementation takes to achieves a good average score for Pong. The DeepMind paper gets to an average of +20 in about 4 hours of training. How does this implementation fair?