Only if you discretize them prematurely. A "true" bayesian, w/ infinite computing power, has exactly one choice; picking their utility f(x).https://twitter.com/enkiv2/status/816405431610445825 …
Yes, but my point was simply that realistic choices shouldn't be prematurely narrowed.
-
-
walking an unusual path through possibility space opens up the unknown.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
possibility space is directed and not very cycle-rich. So, a random walk is very exploratory.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
there are other benefits to ignoring or going against your normal utility function when the stakes are low.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
after all, you share much of your mental model with others but your behaviors operate differently at scale.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
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.