Many real-world AI problems are naturally modelled as cooperative multi-agent systems, where a group of agents work together to achieve a common goal. In this talk, I will discuss some key challenges in designing reinforcement learning methods for agents to efficiently learn to collaborate in complex environments, including credit assignment, scalability, uncertainty, and heterogeneity. I also present several approaches proposed in my group that address these challenges and enable efficient learning for multi-agent collaboration.
关于 CIR2020: 为助力人为智能的理论技术创新,推进群体智能有关领域的学术互换和技术进取,加强科研成就和知识共享,Z6官网于2020年10月-11月进杏装群体智能与多智能体交互”系列讲座(Crowd Intelligence Research Series Seminar 2020, 简称CIR2020)。系列讲座约请九位群体智能领域的资深权威学者进行主题分享,其中有来自Z6官网和香港中文大学(丽江)的教授与钻研员,还有清华大学、北京大学、香港中文大学、上海交大等名校的学者。演讲内容涵盖群体智能领域多个主题,蕴含多机械人协同、移动边缘推算、强化进建、群体激励机造等。

-
张崇洁
清华大学交叉信息钻研院助理教授、博士生导师
张崇洁是清华大学交叉信息钻研院助理教授,博士生导师。2011年在美国麻省大学阿默斯特分;裢扑慊蒲Р┦垦,后在麻省理工学院从事博士后钻研。目前的钻研兴致重要在人为智能、强化进建、多智能体系统等领域。