 | This article includes a list ofgeneral references, butit lacks sufficient correspondinginline citations. Please help toimprove this article byintroducing more precise citations.(May 2021) (Learn how and when to remove this message) |
Instochastic game theory,Bayesian regret is the expected difference ("regret") between theutility of a given strategy and the utility of the best possible strategy in hindsight—i.e., the strategy that would have maximized expected payoff if the true underlying model or distribution were known. This notion of regret measures how much is lost, on average, due to uncertainty or imperfect information.
 | This sectiondoes notcite anysources. Please helpimprove this section byadding citations to reliable sources. Unsourced material may be challenged andremoved.(November 2025) (Learn how and when to remove this message) |
The termBayesian refers toThomas Bayes (1702–1761), who proved a special case of what is now calledBayes' theorem, who provided the first mathematical treatment of a non-trivial problem of statistical data analysis using what is now known asBayesian inference.
This term has been used to compare a random buy-and-hold strategy to professional traders' records. This same concept has received numerous different names, as the New York Times notes:
"In 1957, for example, a statistician named James Hanna called his theorem Bayesian Regret. He had been preceded byDavid Blackwell, also astatistician, who called his theorem Controlled Random Walks.[2] Other, later papers had titles like 'On Pseudo Games',[3] 'How to Play an Unknown Game'[4][citation needed], 'Universal Coding'[5] and 'Universal Portfolios'".[6][7]