TypeError in Wrapper.compute_reward() when running main.py with risc_sd.yaml config

[asxka12]

Dear Chandar-lab,

I hope this message finds you well. I am a beginner in reinforcement learning and have been trying to reproduce the results from your paper. I came across an issue that I am unable to resolve on my own, and I would greatly appreciate your help.

Description of the Issue:
When I run the command python main.py -c configs/risc_sd.yaml, I encounter a TypeError in the Wrapper.compute_reward() function. The error message is as follows:

This error seems to indicate that the compute_reward() method is being called without the necessary desired_goal and info parameters.

Could you please provide some guidance on how to resolve this issue? Are there any specific steps or modifications that I need to make to the code or config file?

Thank you very much for your time and assistance. I am eager to learn and reproduce the results from your paper, and I appreciate any help you can provide.