Risk and Optimal Policies in Bandit Experiments.

We provide a decision‐theoretic analysis of bandit experiments under local asymptotics. Working within the framework of diffusion processes, we define suitable notions of asymptotic Bayes and minimax risk for these experiments. For normally distributed rewards, the minimal Bayes risk can be characte...

Full description

Bibliographic Details

Published in:	Econometrica Vol. 93; no. 3; pp. 1003 - 1030
Main Author:	Adusumilli, Karun
Format:	Article
Published:	Wiley-Blackwell May2025
Subjects:	Decision making Decision theory Multi-armed bandit problem (Probability theory) Bayes' theorem Partial differential equations Feature selection Asymptotic expansions
Online Access:	View this record in EBSCOhost