PAC-Bayesian lifelong learning for multi-armed bandits

DOI10.1007/s10618-022-00825-4zbMath1494.68214arXiv2203.03303OpenAlexW4220868778MaRDI QIDQ2134066

Melih Kandemir, Hamish Flynn, David Reeb, Jan Peters

Publication date: 5 May 2022

Published in: Data Mining and Knowledge Discovery (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2203.03303

zbMATH Keywords

lifelong learningmulti-armed banditsPAC-Bayesian

Mathematics Subject Classification ID

Bayesian inference (62F15) Learning and adaptive systems in artificial intelligence (68T05) Sequential statistical analysis (62L10) Optimal stopping in statistics (62L15)

Uses Software

• Adam

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Doubly robust policy evaluation and optimization
• PAC-Bayesian inequalities of some random variables sequences
• Statistical learning theory and stochastic optimization. Ecole d'Eté de Probabilitiés de Saint-Flour XXXI -- 2001.
• A theory of learning from different domains
• Some PAC-Bayesian theorems
• Weighted sums of certain dependent random variables
• PAC-Bayesian Inequalities for Martingales
• Asymptotic evaluation of certain markov process expectations for large time, I
• Prediction, Learning, and Games

This page was built for publication: PAC-Bayesian lifelong learning for multi-armed bandits