curiosity-driven-exploration-pytorch
curiosity-driven-exploration-pytorch copied to clipboard
Small internal rewards
trafficstars
Int reward values are anomaly small for sparse reward environments. This is normal? if so, why?
Venture example:

Hello, I also encountered the same problem as you. How did you solve it in the end? The rewards from training are the same as yours. I hope to get your reply, which will be very helpful to me.
Hello, unfortunately I don't remember. It was more then 3 years ago:( Try another repo, I guess there are many new curiosity driven agents now