Exploration and incentives in reinforcement learning

DOI10.1287/OPRE.2022.0495MaRDI QIDQ6580506zbMATH OpenFDO

Authors Max Simchowitz, Aleksandrs Slivkins

Publication date 29 July 2024

Published in Operations Research (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1287/OPRE.2022.0495

zbMATH Keywords

Bayesian incentive-compatibilityexploration-exploitation tradeoffincentivized explorationinformation asymmetryinformation designmarket analytics and revenue managementMarkov decision processesmechanism designreinforcement learning

Mathematics Subject Classification ID

Markov and semi-Markov decision processes (90C40)

Recommendations

• Bayesian Incentive-Compatible Bandit Exploration
• Bayesian exploration: incentivizing exploration in Bayesian games
• The Price of Incentivizing Exploration: A Characterization via Thompson Sampling and Sample Complexity
• Incentivizing exploration with heterogeneous value of money
• Bayesian Reinforcement Learning with Exploration

Cited in

(2)

• The Price of Incentivizing Exploration: A Characterization via Thompson Sampling and Sample Complexity
• Near-linear MIR algorithms for stochastically-ordered priors

This page was built for publication: Exploration and incentives in reinforcement learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6580506)