vix.ing · top · new · best · stats · spec

Approximate optimality and the risk/reward tradeoff in a class of bandit problems

2022/10/14 by Zengjing Chen, Larry G. Epstein, Chen, Zengjing +3
Decision Sciences · Economics, Econometrics and Finance · Social Sciences · #Auction Theory and Applications #Economic theories and models #Experimental Behavioral Economics Studies #FOS: Economics and business #FOS: Mathematics #Probability (math.PR) #Theoretical Economics (econ.TH)

paper · pdf · doi:10.48550/arxiv.2210.08077

openalex publication_date 2022/10/14 · openalex created_date 2022/10/20 · openalex updated_date 2026/07/28

Abstract

This paper studies a sequential decision problem where payoff distributions are known and where the riskiness of payoffs matters. Equivalently, it studies sequential choice from a repeated set of independent lotteries. The decision-maker is assumed to pursue strategies that are approximately optimal for large horizons. By exploiting the tractability afforded by asymptotics, conditions are derived characterizing when specialization in one action or lottery throughout is asymptotically optimal and when optimality requires intertemporal diversification. The key is the constancy or variability of risk attitude. The main technical tool is a new central limit theorem.

Related