Bounded Regret for Finitely Parameterized Multi-Armed Bandits

DOI10.1007/978-3-030-98519-6_17OpenAlexW4226365821MaRDI QIDQ5050096

Kishan Panaganti, Dileep Kalathil, Pravin P. Varaiya

Publication date: 15 November 2022

Published in: Stochastic Analysis, Filtering, and Stochastic Optimization (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2003.01328

Mathematics Subject Classification ID

Applications of statistics (62P99) Neural nets and related approaches to inference from stochastic processes (62M45)

Cites Work

• Combinatorial bandits
• Asymptotically efficient adaptive allocation rules
• Decentralized Learning for Multiplayer Multiarmed Bandits
• Asymptotically efficient adaptive allocation schemes for controlled i.i.d. processes: finite parameter space
• High-Dimensional Probability
• Bandit problems with side observations
• Finite-time analysis of the multiarmed bandit problem

This page was built for publication: Bounded Regret for Finitely Parameterized Multi-Armed Bandits