Posit: the conceptual framework of reinforcement learning brings misconceptions about intelligence that have & will set back the field of AI
-
Mainly: casting the end goal of intelligence as the optimization of an extrinsic, scalar reward function. But also:
Show this thread
casting agent(s), environment, and reward, as separate, relatively static entities.
-
-
I'd say intelligence is not an optimization process, and these objects are not the key concepts.
Show this threadThanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
To be fair, we've had that last one with all the previous paradigms too AFAIK.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
totally agree
-
(said while youtube-binging on https://en.m.wikipedia.org/wiki/James_J._Gibson … -related talks)
End of conversation
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.