Reinforcement learning and evolutionary algorithms for non-stationary multi-armed bandit problems

DOI10.1016/J.AMC.2007.07.043MaRDI QIDQ2479159zbMATH OpenOpenAlexFDO

Authors D. E. Koulouriotis, A. Xanthopoulos

Publication date 26 March 2008

Published in Applied Mathematics and Computation (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.amc.2007.07.043

zbMATH Keywords

action selectiondecision-making agentsexploration-exploitationgenetic algorithmsmulti-armed banditreinforcement learning

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Agent technology and artificial intelligence (68T42) Approximation methods and heuristics in mathematical programming (90C59) Decision theory (91B06)

Recommendations

• A comparative study of ad hoc techniques and evolutionary methods for multi-armed bandit problems
• The Nonstochastic Multiarmed Bandit Problem
• Regret analysis of stochastic and nonstochastic multi-armed bandit problems
• Optimal exploration-exploitation in a multi-armed bandit problem with non-stationary rewards
• Thompson Sampling for Bayesian Bandits with Resets

Cites work

• A new approach to the design of reinforcement schemes for learning automata
• Dynamic pricing on the internet: Theory and simulations
• Extensions of the multiarmed bandit problem: The discounted case
• scientific article; zbMATH DE number 4078557 (Why is no real title available?)
• scientific article; zbMATH DE number 1306865 (Why is no real title available?)
• scientific article; zbMATH DE number 194374 (Why is no real title available?)
• Multi-armed bandits in discrete and continuous time
• Switching Costs and the Gittins Index

Cited in

(3)

• Reinforcement learning: exploration-exploitation dilemma in multi-agent foraging task
• Algorithms for recursive delegation
• A comparative study of ad hoc techniques and evolutionary methods for multi-armed bandit problems

This page was built for publication: Reinforcement learning and evolutionary algorithms for non-stationary multi-armed bandit problems

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2479159)