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.
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.
Source: Wikipedia "Bayesian regret" · CC BY-SA 4.0
Share this article: X · Bluesky