That’s precisely my definition for “unriggable” learning processes, in the next post:https://www.lesswrong.com/posts/upLot6eG8cbXdKiFS/reward-function-learning-the-learning-process
That’s a link to this post, right? ;)
Ooops, yes! Sorry, for some reason, I thought this was the post on the value function.
That’s a link to this post, right? ;)
Ooops, yes! Sorry, for some reason, I thought this was the post on the value function.