Satisficing in Time-Sensitive Bandit Learning

DOI10.1287/MOOR.2021.1229MaRDI QIDQ5870357zbMATH OpenOpenAlexFDO

Authors Daniel Russo, Benjamin Van Roy

Publication date 9 January 2023

Published in Mathematics of Operations Research (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1803.02855

zbMATH Keywords

bandit learninginformation theoryonline optimizationrate-distortion theorysatisficingThompson sampling

Mathematics Subject Classification ID

Bayesian problems; characterization of Bayes procedures (62C10) Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• Thompson sampling: an asymptotically optimal finite-time analysis
• Satisficing: a 'pretty good' heuristic
• Multi-objective multi-armed bandit with lexicographically ordered and satisficing objectives
• A learning algorithm for the finite-time two-armed bandit problem
• An information-theoretic analysis of Thompson sampling

Cites work

• X-armed bandits
• A Tutorial on Thompson Sampling
• An information-theoretic analysis of Thompson sampling
• Asymptotically efficient adaptive allocation rules
• Bandit problems with infinitely many arms
• Choosing a good toolkit. I: Prior-free heuristics
• Choosing a good toolkit. II: Bayes-rule based heuristics
• scientific article; zbMATH DE number 5485582 (Why is no real title available?)
• Kullback-Leibler upper confidence bounds for optimal sequential allocation
• Learning to optimize via posterior sampling
• Linearly parameterized bandits
• On the complexity of best-arm identification in multi-armed bandit models
• Regret analysis of stochastic and nonstochastic multi-armed bandit problems
• The knowledge gradient algorithm for a general class of online learning problems

Cited in

(3)

• Multi-objective multi-armed bandit with lexicographically ordered and satisficing objectives
• Reinforcement Learning, Bit by Bit
• Information-directed sampling for bandits: a primer

This page was built for publication: Satisficing in Time-Sensitive Bandit Learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5870357)