News for hackers. Stuff that matters.
Re:Why traditional reinforcement learning will probably not ... by sn41 on Wednesday October 21, 2020 @07:30PM (#24853441)
I think you are right in constructing situations where real numbers are inadequate. It is also right that you do not claim that hyperreals or surreals suffice, you are merely pointing out that they may help you to do better than the reals.

But I have often wondered - why are people hung up on linear ordering? Why not non-total partial orders?

https://en.wikipedia.org/wiki/Ordinal_optimization

Is this insistence on linear orders because of simplistic modeling on the part of cognitive science and AI people, or is there some problem with general partial orders?

Re:Why traditional reinforcement learning will probably not ... by xamuel on Wednesday October 21, 2020 @09:13PM (#24854007)
One could certainly contemplate versions of RL with non-linear orderings. I guess the reason people care about linear ordering is because you want the agent to at least understand "this outcome is better than that outcome". How would we hope for a good nonlinear-RL agent to behave in an environment with 2 buttons, one of which always gives reward X, and the other of which always gives reward Y, where X and Y are incomparable?
Re:Why traditional reinforcement learning will probably not ... by sn41 on Thursday October 22, 2020 @12:51AM (#24854992)
That's understandable. But many decisions in life are like that. Do you want to be close to your roots and your parents, or do you want a high-flying career in a remote city? Choices involve sacrifices as well as gains, and many meaningful outcomes are incomparable among themselves.