SEMINAR: Multiagent Learning for the Emergence of Social Norms in Networked MASs
PRESENTER: Dr. Chao Yu (School of Computer Science and Technology as a lecturer at Dalian University of Technology, China)
WHERE: Building 3, Room 224
WHEN: 11:00 AM ~ 12:00 PM, Monday, 30th November 2015
ABSTRACT: In multiagent systems (MASs), social norms serve as an important technique in regulating agents' behaviours to ensure effective coordination among agents without a centralized controlling mechanism. In such a distributed environment, it is important to investigate how a desirable social norm can emerge in a bottom-up manner among agents through repeated local interactions and learning techniques. Understanding efficient mechanisms of norm emergence can not only provide us with a better understanding of the formation and evolution process of opinions, conventions, and rules in human societies, but also enable us to build and control large-scale MASs. In this talk, several effective multiagent learning (MAL) mechanisms that are capable of facilitating the emergence of social norms in networked MASs will be introduced. These mechanisms include a collective interaction protocol, a hierarchical supervision framework and a layered adaptive learning framework. Experimental results show that these mechanisms are effective for emerging robust norms in networked MASs.
BIO: Dr. Chao Yu received his PhD degree in Computer Science from the University of Wollongong, Australia, in December 2013. Prior to that, he got his BSc degree from the Huazhong University of Science and Technology, China, in 2007, MSc degree from the Huazhong Normal University, China, in 2010. In March 2014, he joined the School of Computer Science and Technology as a lecturer at Dalian University of Technology, China. He is the principle investigator of several competitive projects in China, supported by the National Natural Science Foundation of China and Fundamental Research Funds for the Central Universities of China. He has published over 30 papers in rigorously refereed journals and conferences, including IEEE TNNLS, IEEE T CYB, and AAMAS. His research interests include Multiagent Systems and Multiagent Learning, with their wide applications in modeling and solving various real-world problems such as Social Internet of Things and Vehicular Networking.