Prof. Yang Gao, who is the deputy director of Department of Computer Science of Nanjing University, China, gave a talk on December 17th in Xianlin campus, Nanjing Normal University. The topic of this talk is “Game and Equilibrium in Multi-Agent Reinforcement Learning”. Prof. Ming Yang hosted the talk.
Prof. Gao received the Ph.D. degree from the Department of Computer Science, Nanjing University, in 2000. Currently, He is a Professor, and also the deputy director in the department of computer science, Nanjing University. Prof. Gao was selected into the “New Century Elite Talents Support Program” from Ministry of Education, in 2010. He is currently directing the Reasoning and Learning Research Group in Nanjing University. He has published more than 100 papers in top-tired conferences and journals (e.g., IEEE TPAMI, IEEE TNNLS, IEEE TCYB, PR, AAAI, CVPR, AAMAS, ACMMM, etc.). His current research interests include artificial intelligence and machine learning. He also serves as Program Chair and Area Chair for many international conferences.
During the talk, Prof. Gao mainly introduced the principle of reinforcement learning and the multi-agent reinforcement learning algorithms. Also, he shared several novel works of his team in the multi-agent reinforcement learning: a non-shared payment matrix game algorithm, an approximate game algorithm, as well as the game migration and game reduction algorithm.
After the talk, Prof. Gao had a discussion with the audiences and answered their questions in details. This talk enables the teachers and graduates to improve their understanding of game and equilibrium in multi-agent reinforcement learning. It also provides valuable suggestions and much inspiration for our researchers.