We are very excited to announce the next talk of the series “Games, Decisions & Networks”, which will be given this Friday, June 11th at noon 12:00 PM EST by Prof. Na Li (Harvard University). Please find the talk information as follows:
Title: Gradient Play in Multi-Agent Stochastic Games: Stationary Points and Convergence
Abstract: We study the performance of the gradient play algorithm for multi-agent tabular Markov decision processes (MDPs), which are also known as stochastic games (SGs), where each agent tries to maximize its own total discounted reward by making decisions independently based on current state information which is shared between agents. Policies are directly parameterized by the probability of choosing a certain action at a given state. We show that Nash equilibria (NEs) and first-order stationary policies are equivalent in this setting, and give a non-asymptotic global convergence rate analysis to an epsilon-NE for a subclass of multi-agent MDPs called Markov Potential Games (MPG), which includes the cooperative setting with identical rewards among agents as an important special case. Our result shows that the number of iterations to reach an epsilon-NE scales linearly, instead of exponentially, with the number of agents. Local geometry and local stability are also considered. We also show that strict NEs are local maxima of the total potential function and fully-mixed NEs are saddle points. Lastly, we give a local convergence rate around strict NEs for more general settings.
Joint work with Runyu (Cathy) Zhang and Zhaolin Ren.
Bio: Na Li is a Gordon McKay professor in Electrical Engineering and Applied Mathematics at Harvard University. She received her Bachelor degree in Mathematics from Zhejiang University in 2007 and Ph.D. degree in Control and Dynamical systems from California Institute of Technology in 2013. She was a postdoctoral associate at Massachusetts Institute of Technology 2013-2014. Her research lies in control, learning, and optimization of networked systems, including theory development, algorithm design, and applications to real-world cyber-physical societal system. She received NSF career award (2016), AFSOR Young Investigator Award (2017), ONR Young Investigator Award(2019), Donald P. Eckman Award (2019), McDonald Mentoring Award (2020), along with some other awards.
You can participate in the seminar via Zoom at:
https://mit.zoom.us/j/97956989953, or watch the Youtube livestream at:
https://youtu.be/MQw4tZ0gZD0. The links can also be found at our website:
https://sites.google.com/view/gamesdecisionsnetworks.--
FROM 202.121.181.*