Thompson Sampling for Bayesian Bandits with Resets

DOI10.1007/978-3-642-41575-3_31MaRDI QIDQ2868572zbMATH OpenOpenAlexFDO

Authors Paolo Viappiani

Publication date 17 December 2013

Published in Algorithmic Decision Theory (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/978-3-642-41575-3_31

zbMATH Keywords

Bayesian banditsexploitationexplorationmulti-armed bandit problemThompson sampling

Mathematics Subject Classification ID

Sequential statistical analysis (62L10) Software, source code, etc. for problems pertaining to game theory, economics, and finance (91-04) Probabilistic games; gambling (91A60)

Recommendations

• scientific article; zbMATH DE number 7626733
• Near-optimal regret bounds for Thompson sampling
• Linear Thompson sampling revisited
• Thompson Sampling for Stochastic Control: The Continuous Parameter Case
• Thompson Sampling for Stochastic Control: The Finite Parameter Case
• A Tutorial on Thompson Sampling
• Thompson sampling: an asymptotically optimal finite-time analysis
• Feel-Good Thompson Sampling for Contextual Bandits and Reinforcement Learning
• On the Prior Sensitivity of Thompson Sampling
• Sliding-Window Thompson Sampling for Non-Stationary Settings

Cited in

(7)

• Linear Thompson sampling revisited
• Reinforcement learning and evolutionary algorithms for non-stationary multi-armed bandit problems
• An information-theoretic analysis of Thompson sampling
• On the Prior Sensitivity of Thompson Sampling
• A Tutorial on Thompson Sampling
• Sliding-Window Thompson Sampling for Non-Stationary Settings
• Continual learning as computationally constrained reinforcement learning

This page was built for publication: Thompson Sampling for Bayesian Bandits with Resets

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2868572)