关于举办胡舒悦博士学术报告会的通知

发布时间:2022-07-04 浏览次数:11

时间:2022年741030-1130

地点:B7-303会议室

主持人:蔡毅

 

报告题目:

The Dynamics of Q-learning in Population Games: a Physics-inspired Continuity Equation Model

 

摘要:

Although learning has found wide application in multi-agent systems, its effects on the temporal evolution of a system are far from understood. This paper focuses on the dynamics of Q-learning in large-scale multi-agent systems modeled as population games. We revisit the replicator equation model for Q-learning dynamics and observe that this model is inappropriate for our concerned setting. Motivated by this, we develop a new formal model, which bears a formal connection with the continuity equation in physics. We show that our model always accurately describes the Q-learning dynamics in population games across different initial settings of MASs and game configurations. We also show that our model can be applied to different exploration mechanisms, describe the mean dynamics, and be extended to Q-learning in 2-player and n-player games. Last but not least, we show that our model can provide insights into algorithm parameters and facilitate parameter tuning.

 

个人简介:

Shuyue Hu, a researcher at Shanghai Artificial Intelligence Laboratory in Shanghai, China. Previously, she was a postdoctoral research fellow working with Prof. Georgios Piliouras and Prof. Harold Soh at Singapore University of Technology and Design and National University of Singapore, respectively. She completed her Ph.D at the Chinese University of Hong Kong in December 2019, and received her bachelor degree at the South China University of Technology in July 2015. Her research interests are broadly in game theory, multi-agent systems, and reinforcement learning.


TOP