PAC-Bayesian Analysis of the Exploration-Exploitation Trade-off

2011/05/23 by Yevgeny Seldin, Nicolò Cesa‐Bianchi, Seldin, Yevgeny +9 · 1 citation
Computer Science · Decision Sciences · #Advanced Bandit Algorithms Research #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine Learning and Algorithms #Reinforcement Learning in Robotics

paper · pdf · doi:10.48550/arxiv.1105.4585

openalex publication_date 2011/05/23 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

We develop a coherent framework for integrative simultaneous analysis of the exploration-exploitation and model order selection trade-offs. We improve over our preceding results on the same subject (Seldin et al., 2011) by combining PAC-Bayesian analysis with Bernstein-type inequality for martingales. Such a combination is also of independent interest for studies of multiple simultaneously evolving martingales.

Citations

• The Nonstochastic Multiarmed Bandit Problem

Cited by

• Bayesian Reinforcement Learning: A Survey

Related

• PAC-Bayes-Bernstein Inequality for Martingales and its Application to\n Multiarmed Bandits
• PAC-Bayesian Analysis of Martingales and Multiarmed Bandits
• PAC-Bayesian Inequalities for Martingales
• Mastering the exploration-exploitation trade-off in Bayesian Optimization
• PAC-Bayesian aggregation and multi-armed bandits