Sign in
Improved High-Probability Regret for Adversarial Bandits with Time-Varying Feedback Graphs
Conference proceeding

Improved High-Probability Regret for Adversarial Bandits with Time-Varying Feedback Graphs

Haipeng Luo, Hanghang Tong, Mengxiao Zhang and Yuheng Zhang
INTERNATIONAL CONFERENCE ON ALGORITHMIC LEARNING THEORY, Vol.201, pp.1074-1100
Proceedings of Machine Learning Research
01/01/2023

View Online

Abstract

Computer Science Technology Computer Science, Information Systems Computer Science, Theory & Methods Science & Technology

Details

Metrics

1 Record Views