上海科技大学 | English | 地图
首页> 新闻信息> 活动
Multi-Agent Machine Learning: A Tutorial
Date:2018/4/10     Browse:179

Speaker:     Prof. Jun Wang, UCL

Time:          Apr 10, 13:30—14:30

Location:    Room 1C-502, SIST Building

Host:          Prof. Xiliang Luo

Abstract:

Multi-agent learning arises in a variety of domains with the applications ranging from controlling a group of autonomous vehicles/robots/drones, military combats, collaborative bots in production lines to optimizing distributed sensor networks/traffic and to machine bidding in competitive e-commerce and financial markets, just to name a few. In this talk, I shall provide an up-to-date tutorial on the technique and algorithms of multi-agent AI, with a focus on competition, collaboration, and communications among intelligent agents. The studies in both game theory and machine learning will be examined and be presented in a unified treatment. At the end of the talk, I shall example our recent work on the subject including mean-field multi-agent reinforcement learning, generative adversarial nets, hierarchical reinforcement learning and their applications in various domains.

Bio:

Dr. Jun Wang obtained his PhD degree in Delft University of Technology, the Netherlands; MSc degree in National University of Singapore, Singapore; and Bachelor degree in Southeast University, Nanjing, China. Currently, he is Chair Professor of Data Science, Computer Science, University College London, and Founding Director of MSc Web Science and Big Data Analytics. He is also Co-founder and Chief Scientist in MediaGamma Ltd, a UCL spin-out focusing on AI for intelligent audience decision making. His team won the first global real-time bidding algorithm contest with 80+ participants worldwide. He was a recipient of the Beyond Search Semantic Computing and Internet Economics award by Microsoft Research and also received Yahoo! FREP Faculty award. He has served as an Area Chair in ACM CIKM and ACM SIGIR. He was a technical advisor for startups such as Last.Fm, Passiv Systems, Massive Analytic, Context Scout, and Polecat, and had various projects with BT, Microsoft, Yahoo!, Alibaba etc. 

SIST-Seminar 18018