Biography
Vijay Gupta is the Elmore Professor in the School of Electrical and Computer Engineering at Purdue. He received his B. Tech degree at Indian Institute of Technology, Delhi, and his M.S. and Ph.D. at California Institute of Technology, all in Electrical Engineering. He received the 2018 Antonio Ruberti Award from IEEE Control Systems Society, the 2013 Donald P. Eckman Award from the American Automatic Control Council and a 2009 National Science Foundation (NSF) CAREER Award. His research and teaching interests are broadly in distributed decision making.
Abstract
Many learning algorithms have been proposed for design of control policies in cooperative and competitive multi-agent systems. We explore the robustness of some such algorithms to the presence of strategic agents. First, we show that the recently proposed multi-agent reinforcement learning algorithms are vulnerable to being hijacked by even one agent that prioritizes individual utility function over the team utility function. Then we consider a game set up in which agents are employing a fictitious play-based learning algorithm and show that an agent can move the game to a more favorable equilibrium by deviating from the prescribed algorithm.
