4 papers
Decentralized Asynchronous Multi-player Bandits
Jingqi Fan, Canzhe Zhao, Shuai Li +1
In recent years, multi-player multi-armed bandits (MP-MAB) have been extensively studied due to their wide applications in cognitive radio networks and Internet of Things systems.…
A New Structure for the 2D water wave equation: Energy stability and Global well-posedness
Qingtang Su, Siwei Wang
We study the two-dimensional gravity water waves with a one-dimensional interface with small initial data. Our main contributions include the development of two novel localization…
Learning with Limited Shared Information in Multi-agent Multi-armed Bandit
Junning Shao, Siwei Wang, Zhixuan Fang
Multi-agent multi-armed bandit (MAMAB) is a classic collaborative learning model and has gained much attention in recent years. However, existing studies do not consider the case w…
Efficient and Optimal Policy Gradient Algorithm for Corrupted Multi-armed Bandits
Jiayuan Liu, Siwei Wang, Zhixuan Fang
In this paper, we consider the stochastic multi-armed bandits problem with adversarial corruptions, where the random rewards of the arms are partially modified by an adversary to f…