[Feature Request] DQN Loss importance sampling

[monney]

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

• [x] I have checked that there is no similar issue in the repo (required)

[vmoens]

I will take a look into this thanks for sharing!

[monney]

Thank you!