Switching Costs and the Gittins Index

DOI10.2307/2951664zbMath0807.90123OpenAlexW2021622496MaRDI QIDQ4301032

Rangarajan K. Sundaram, Jeffrey S. Banks

Publication date: 19 February 1995

Published in: Econometrica (Search for Journal in Brave)

Full work available at URL: https://authors.library.caltech.edu/67329/

zbMATH Keywords

infinite horizonGittins indexswitching costsgeometric discountingindependent-armed bandit problemsindex strategies

Mathematics Subject Classification ID

Markov and semi-Markov decision processes (90C40)

Related Items (22)

Optimal learning and experimentation in bandit problems. ⋮ Strategic conversations under imperfect information: epistemic message exchange games ⋮ Multi-armed bandit processes with optimal selection of the operating times ⋮ Optimal learning with costly adjustment ⋮ Keeping your options open ⋮ A perpetual search for talents across overlapping generations: a learning process ⋮ THE FAIR REWARD PROBLEM: THE ILLUSION OF SUCCESS AND HOW TO SOLVE IT ⋮ Index policies for discounted bandit problems with availability constraints ⋮ Optimal hysteresis for a class of deterministic deteriorating two-armed bandit problem with switching costs. ⋮ Branching bandits: A sequential search process with correlated pay-offs. ⋮ Dynamic priority allocation via restless bandit marginal productivity indices ⋮ Some indexable families of restless bandit problems ⋮ A comparative study of ad hoc techniques and evolutionary methods for multi-armed bandit problems ⋮ Reinforcement learning and evolutionary algorithms for non-stationary multi-armed bandit problems ⋮ Stationary multi-choice bandit problems. ⋮ Response adaptive designs that incorporate switching costs and constraints ⋮ On the (non-) reliance on algorithms -- a decision-theoretic account ⋮ Two-Armed Restless Bandits with Imperfect Information: Stochastic Control and Indexability ⋮ Prakash and Sertel's theory of non-cooperative equilibria in social systems --- twenty years later ⋮ Generalized Bandit Problems ⋮ Gittins Index for Simple Family of Markov Bandit Processes with Switching Cost and No Discounting ⋮ A General Theory of MultiArmed Bandit Processes with Constrained Arm Switches

This page was built for publication: Switching Costs and the Gittins Index