Switching Costs and the Gittins Index

DOI10.2307/2951664zbMATH Open0807.90123OpenAlexW2021622496MaRDI QIDQ4301032FDOQ4301032

Authors: Jeffrey S. Banks, Rangarajan K. Sundaram 

Publication date: 19 February 1995

Published in: Econometrica (Search for Journal in Brave)

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

Recommendations

• Gittins Index for Simple Family of Markov Bandit Processes with Switching Cost and No Discounting
• Generalized Bandit Problems
• Stationary multi-choice bandit problems.
• A faster index algorithm and a computational study for bandits with switching costs
• Multi-armed bandits with switching penalties

zbMATH Keywords

Gittins indexswitching costsinfinite horizongeometric discountingindependent-armed bandit problemsindex strategies

Mathematics Subject Classification ID

Markov and semi-Markov decision processes (90C40)

Cited In (23)

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

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

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4301032)