Distributed Learning for Multi-Cluster and Online Games

报告人：孟 敏 同济大学

个人简介：

孟敏，同济大学教授，博导，自主智能无人系统全国重点实验室，电子与信息工程学院、自主智能无人系统科学中心。于2015年获得山东大学数学学院理学博士，2015年至2017年多次访问香港大学、香港城市大学，2017年至2020年在南洋理工大学做博士后，于2020年9月加入同济大学。入选国家级青年人才、中国科协“青托”、上海市浦江人才计划、上海市领军人才，主持国家自然科学基金青年基金，获山东省科学技术奖自然科学奖二等奖（第二位）、中国自动化学会自然科学奖二等奖（第二位），为中国自动化学会青年工作委员会、女科技工作者委员会委员。目前为Journal of The Franklin Institute 和Franklin Open副编委（Associate Editor）。 长期从事逻辑网络、分布式博弈与优化、分布式安全估计与控制等研究。

报告摘要：This talk discusses the distributed strategy design for Nash equilibrium (NE) seeking in two kinds of complex games, multi-cluster games and online games. In a multi-cluster game, there are multiple clusters and each cluster consists of a group of agents. A cluster is viewed as a virtual noncooperative player that aims to minimize its local payoff function and the agents in a cluster are the actual players that cooperate within the cluster to optimize the payoff function of the cluster through communication via a connected graph. To solve the NE seeking problem of this formulated game, a discrete-time distributed algorithm, called distributed gradient tracking algorithm, is devised based on the inter- and intra-communication of clusters, and is shown to converge at a linear rate. In addition, considering time-varying payoff functions and constraints in online games, a novel distributed online learning algorithm for seeking NE is proposed. It is proved that the presented algorithm can achieve sublinear bounded dynamic regrets and constraint violation.