CS 285: Lecture 15, Part 1: Offline Reinforcement Learning

[@baselomari3657]

At 33:16, shouldn't it be "x*

[@ResidualSkill]

yeah seems like a typo

[@dwpark3761]

I don't think so. It is some kind of analogy. Just imagine that f(x) is Q(s,a) in the next page.

[@binyuwang6563]

It's not a typo. Here x*

[@SphereofTime]

1:00

[@AmitSingh-jo8ob]

Is there a page by lab where i can see all these references (that are being used in slide) at one place?
Also, is there a servey paper covers all these things?