Thanks, Also I was running the code on the no_intervention setting, using the command run_rl_training no_intervention However, I am seeing almost zero reward hacking in my run: Am I doing something wrong here?
It’s hard for me to help without more information. I’ve responded to your email asking to send some of the files created by training, I can try to help you debug from there.
Thanks,
Also I was running the code on the no_intervention setting, using the command
run_rl_training no_interventionHowever, I am seeing almost zero reward hacking in my run:
Am I doing something wrong here?
It’s hard for me to help without more information. I’ve responded to your email asking to send some of the files created by training, I can try to help you debug from there.