Open monney opened 1 year ago
I believe the current DQN Losses don't apply importance sampling weights. This is almost always applied when using a PER Buffer.
The PER buffer outputs "_weight" in info, this if in inputTensorDict, could be applied at time of loss calculation
element-wise loss could be returned with any transforms or weighting to be applied later on
I will take a look into this thanks for sharing!
Thank you!
Motivation
I believe the current DQN Losses don't apply importance sampling weights. This is almost always applied when using a PER Buffer.
Solution
The PER buffer outputs "_weight" in info, this if in inputTensorDict, could be applied at time of loss calculation
Alternatives
element-wise loss could be returned with any transforms or weighting to be applied later on
Checklist