Adithya

> I found a solution for this. I changed the action call method (according to this: https://docs.ray.io/en/master/rllib/rllib-training.html) as below: > > from ray.rllib.core.rl_module import RLModule > > > # Create...

Does that really work? I have been looking for viable work-arounds.

> Hi [@AdithyaRaman](https://github.com/AdithyaRaman) No, actually when you use New API stack these will be created automatically in saved training directory , somewhere in your temp directory. It is as below:...

> I think your problem is something between the trained model and your environment. Why it should give you a vector with 4 when you pass your environment with an...

Hi, I am facing a similar issue when I am using the amdsmi python library to track the energy consumption. I wrote a python script that reads the energy counter...

THIS IS IT! I had to multiply the the counter with the resolution and now the result matches the reported energy from both AMD-SMI CLI and ROCM-SMI CLI, passing the...