Tuning Bandit Algorithms in Stochastic Environments

DOI10.1007/978-3-540-75225-7_15MaRDI QIDQ3520056zbMATH OpenOpenAlexFDO

Authors Jean-Yves Audibert, Rémi Munos, Csaba Szepesvári

Publication date 19 August 2008

Published in Lecture Notes in Computer Science (Search for Journal in Brave)

Full work available at URL https://hal.inria.fr/inria-00203487/file/ucb_alt.pdf

Mathematics Subject Classification ID

Stopping times; optimal stopping problems; gambling theory (60G40) Computational learning theory (68Q32)

Recommendations

• Exploration-exploitation tradeoff using variance estimates in multi-armed bandits
• UCB revisited: improved regret bounds for the stochastic multi-armed bandit problem
• Kullback-Leibler upper confidence bounds for optimal sequential allocation
• On upper-confidence bound policies for switching bandit problems
• Upper-Confidence-Bound Algorithms for Active Learning in Multi-armed Bandits

Cites work

• Asymptotically efficient adaptive allocation rules
• Finite-time analysis of the multiarmed bandit problem
• Machine learning and nonparametric bandit theory
• Sample mean based index policies by O(log n) regret for the multi-armed bandit problem
• Some aspects of the sequential design of experiments

Cited in

(20)

• Exploration-exploitation tradeoff using variance estimates in multi-armed bandits
• A penalized bandit algorithm
• Detecting concept change in dynamic data streams
• Preference-based reinforcement learning: evolutionary direct policy search using a preference-based racing algorithm
• Faster Hoeffding racing: Bernstein races via jackknife estimates
• On upper-confidence bound policies for switching bandit problems
• Reward-modulated Hebbian learning of decision making
• Kullback-Leibler upper confidence bounds for optimal sequential allocation
• Robustness of stochastic bandit policies
• scientific article; zbMATH DE number 6982311 (Why is no real title available?)
• 10.1162/153244303321897663
• scientific article; zbMATH DE number 7596797 (Why is no real title available?)
• scientific article; zbMATH DE number 6253908 (Why is no real title available?)
• AI-driven liquidity provision in OTC financial markets
• Analyzing bandit-based adaptive operator selection mechanisms
• Corruption-tolerant bandit learning
• Variance-aware estimation of kernel mean embedding
• An exponential Efron-Stein inequality for L_q stable learning rules
• Empirical Bernstein and betting confidence intervals for randomized quasi-Monte Carlo
• Empirical Bernstein in smooth Banach spaces

This page was built for publication: Tuning Bandit Algorithms in Stochastic Environments

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3520056)