Issue when trying to run cadrl as policy for human agents

[fb1812]

Hi,

I am trying to run experiments where the human agents are running cadrl as policy instead of Orca .
However, I keep running into issues where the variable self.env is None when trying to update the step of each agent with the trained cadrl policy.

Do you have any clue on how I can solve this issue?

Thank you !

[ChanganVR]

@fb1812 have you figured it out? I don't have a clue since it's been a while since I touched the code. If you share the command you run, I can look into it over the weekend.