Feel-Good Thompson Sampling for Contextual Bandits and Reinforcement Learning

DOI10.1137/21M140924XMaRDI QIDQ5089723zbMATH OpenOpenAlexFDO

Authors

Publication date 15 July 2022

Published in SIAM Journal on Mathematics of Data Science (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/2110.00871

zbMATH Keywords

contextual banditsreinforcement learningThompson sampling

Mathematics Subject Classification ID

Computational learning theory (68Q32) Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• Near-optimal regret bounds for Thompson sampling
• An information-theoretic analysis of Thompson sampling
• On the Prior Sensitivity of Thompson Sampling
• Thompson sampling: an asymptotically optimal finite-time analysis
• Linear Thompson sampling revisited

Cites work

• 10.1162/153244303321897663
• A decision-theoretic generalization of on-line learning and an application to boosting
• An information-theoretic analysis of Thompson sampling
• Bypassing the Monster: A Faster and Simpler Optimal Algorithm for Contextual Bandits Under Realizability
• Competitive On-line Statistics
• Deep exploration via randomized value functions
• Information-theoretic determination of minimax rates of convergence
• Learning to optimize via posterior sampling
• The Nonstochastic Multiarmed Bandit Problem

Cited in

(6)

• On the Prior Sensitivity of Thompson Sampling
• Thompson Sampling for Bayesian Bandits with Resets
• A Tutorial on Thompson Sampling
• Bayesian design principles for frequentist sequential learning
• Unified algorithms for RL with decision-estimation coefficients: PAC, reward-free, preference-based learning and beyond
• Adaptive network approach to exploration-exploitation trade-off in reinforcement learning

This page was built for publication: Feel-Good Thompson Sampling for Contextual Bandits and Reinforcement Learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5089723)