A bandit problem is interesting only if there are arms with unknown characteristics. To choose among the available arms a decision maker must first decide how to handle this uncertainty. In the first eight chapters of this monograph the approach used is to average the payoff over the unknown characteristics with respect to a specified prior distribution — a Bayesian approach, in statistical parlance.
CITATION STYLE
Berry, D. A., & Fristedt, B. (1985). Minimax Approach. In Bandit problems (pp. 191–206). Springer Netherlands. https://doi.org/10.1007/978-94-015-3711-7_9
Mendeley helps you to discover research relevant for your work.