📑 Table of Contents▼

In stochastic game theory, Bayesian regret is the expected difference ("regret") between the utility 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.

Etymology

edit

The term Bayesian refers to Thomas Bayes (1702–1761), who proved a special case of what is now called Bayes' theorem, who provided the first mathematical treatment of a non-trivial problem of statistical data analysis using what is now known as Bayesian inference.

Economics

edit

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 by David Blackwell, also a statistician, who called his theorem Controlled Random Walks.[1] Other, later papers had titles like 'On Pseudo Games',[2] 'How to Play an Unknown Game'[3], 'Universal Coding'[4] and 'Universal Portfolios'".[5][6]

References

edit
  1. ^ Blackwell, David (1954). Controlled random walks (PDF). Proceedings of the International Congress of Mathematicians. Vol. 3. pp. 336–338.
  2. ^ Banos, Alfredo (December 1968). "On Pseudo-Games". The Annals of Mathematical Statistics. 39 (6): 1932–1945. doi:10.1214/aoms/1177698023. ISSN 0003-4851.
  3. ^ Harsanyi, John C. (1982), "Games with Incomplete Information Played by "Bayesian" Players, I–III Part I. The Basic Model", Papers in Game Theory, Dordrecht: Springer Netherlands, pp. 115–138, doi:10.1007/978-94-017-2527-9_6, ISBN 978-90-481-8369-2, retrieved 2023-06-13{{citation}}: CS1 maint: work parameter with ISBN (link)
  4. ^ Rissanen, J. (July 1984). "Universal coding, information, prediction, and estimation". IEEE Transactions on Information Theory. 30 (4): 629–636. Bibcode:1984ITIT...30..629R. doi:10.1109/TIT.1984.1056936. ISSN 1557-9654. S2CID 206735464.
  5. ^ Cover, Thomas M. (January 1991). "Universal Portfolios". Mathematical Finance. 1 (1): 1–29. doi:10.1111/j.1467-9965.1991.tb00002.x. ISSN 0960-1627. S2CID 219967240.
  6. ^ Kolata, Gina (2006-02-05). "Pity the Scientist Who Discovers the Discovered". The New York Times. ISSN 0362-4331. Retrieved 2017-02-27.

📚 Artikel Terkait di Wikipedia

Thompson sampling

property, one can translate regret bounds established for UCB algorithms to Bayesian regret bounds for Thompson sampling or unify regret analysis across both

Perfect Bayesian equilibrium

In game theory, a Perfect Bayesian Equilibrium (PBE) is a solution with Bayesian probability to a turn-based game with incomplete information. More specifically

Bayesian game

In game theory, a Bayesian game is a strategic decision-making model which assumes players have incomplete information. Players may hold private information

Complete information

games), these solutions turn towards Bayesian Nash Equilibria since games with incomplete information become Bayesian games. In a game of complete information

Bayes correlated equilibrium

perfect-information solution concept to bayesian games, and also a broader solution concept than the usual Bayesian Nash equilibrium thereof. Additionally

Bayesian optimization

Bayesian optimization is a sequential design strategy for global optimization of black-box functions, that does not assume any functional forms. It is

Prisoner's dilemma

[citation needed] Deriving the optimal strategy is generally done in two ways: Bayesian Nash equilibrium: If the statistical distribution of opposing strategies

Paradox of tolerance

Game theorists Games Traditional game theory Definitions Asynchrony Bayesian regret Best response Bounded rationality Cheap talk Coalition Complete contract