 Follow-the-Perturbed-Leader for Adversarial Markov Decision Processes
with Bandit FeedbackNeural Information Processing Systems (NeurIPS), 2022 |
 Online Boosting with Bandit FeedbackInternational Conference on Algorithmic Learning Theory (ALT), 2020 |
 Efficient and Robust Algorithms for Adversarial Linear Contextual
BanditsAnnual Conference Computational Learning Theory (COLT), 2020 |
 Minimax Optimal Algorithms for Adversarial Bandit Problem with Multiple
PlaysIEEE Transactions on Signal Processing (IEEE Trans. Signal Process.), 2019 |
 Tight Bounds for Bandit Combinatorial OptimizationAnnual Conference Computational Learning Theory (COLT), 2017 |
