Utility theory is agnostic about the content of preferences. It is perfectly consistent with utility theory for an agent to want to kill itself. Or to do something which leads to its death.
-
-
How is utility different from loss function? The latter is ConstructedWithMinimizationInMind. It is difficult to look at loss function in ML in any other way -- that construction is its defining characteristic.
-
Well utility theory goes through the trouble to derive utility functions from ordinal preferences. But I'm not sure I get your point with this comparison
- 3 more replies
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.