Talk:Optimal decision

Notation for expected utility

Currently the article uses one piece of notation for two different things: $U_{D}(d)$ means both utility and expected utility. It is standard in the optimization literature to denote expected utility as the expected value of utility: ${\text{E}}U_{D}(d).$ I fixed the notational inconsistency by inserting the expectations operator, but this fix was reverted by Winterfors without explanation. Can you explain why? Loraof (talk) 16:10, 19 May 2015 (UTC)

Thanks for your edits, I reverted this particular one because ${\text{E}}U_{D}(d).$ gives the impression of being an expectation over the space of possible decision $D$, when the expectation is taken over the space of possible outcomes $O$. I agree that including the expectation in the notation might be a good idea, but it needs to be clear on what variable it operates.Winterfors (talk) 18:23, 19 May 2015 (UTC)