Sliding-Window Thompson Sampling for Non-Stationary Settings

DOI10.1613/JAIR.1.11407MaRDI QIDQ5114784zbMATH OpenOpenAlexFDO

Authors Francesco Trovò, Marcello Restelli, Nicola Gatti

Publication date 26 June 2020

Published in Journal of Artificial Intelligence Research (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1613/jair.1.11407

zbMATH Keywords

sequential decision problemThompson sampling

Mathematics Subject Classification ID

Sampling theory, sample surveys (62D05) Sequential estimation (62L12)

Recommendations

• scientific article; zbMATH DE number 7626733
• Thompson Sampling for Bayesian Bandits with Resets
• Thompson Sampling for Stochastic Control: The Continuous Parameter Case
• Thompson Sampling for Stochastic Control: The Finite Parameter Case
• Linear Thompson sampling revisited
• Thompson sampling: an asymptotically optimal finite-time analysis
• Near-optimal regret bounds for Thompson sampling
• A Tutorial on Thompson Sampling
• On the Prior Sensitivity of Thompson Sampling

Cited in

(9)

• Thompson Sampling for Bayesian Bandits with Resets
• time-decaying bandits for non-stationary problems
• On upper-confidence bound policies for switching bandit problems
• Recurrent Neural-Linear Posterior Sampling for Nonstationary Contextual Bandits
• Multi-armed bandit problem with online clustering as side information
• Continual learning as computationally constrained reinforcement learning
• Collective intelligence in decision-making with non-stationary experts
• Adaptive smooth nonstationary bandits
• Adaptive neighborhood selection for MAPF via non-stationary bandits

This page was built for publication: Sliding-Window Thompson Sampling for Non-Stationary Settings

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5114784)