-
Hi everyone! Haven't asked a question here in a while, I hope you missed me 😇 I'm training an actor-critic agent. Every time I train the actor, I want to train the critic as many times as needed until it reaches a good representation of the Q values of the environment. This could be one iterations or 100 iterations. I currenly run these iterations using |
Beta Was this translation helpful? Give feedback.
Replies: 1 comment
-
Oh, I discovered |
Beta Was this translation helpful? Give feedback.
Oh, I discovered
while_loop
! That's probably the solution to my problem. Thanks anyway.