Intrinsic Reward in ICM

How severe does this issue affect your experience of using Ray?

  • Medium: It contributes to significant difficulty to complete my task, but I can work around it.

I was trying to train PPO + Curiosity (ICM) on a no-reward environment using Tune but the printed reward is always zero (including min and max rewards). Is it printing just the extrinsic reward or the sum intrinsic+extrinsic?
If it is just extrinsic (in that case it makes sense that it shows zero), how do I get it to log intrinsic reward too?