Theoretical Foundations of Multiagent Reinforcement Learning
Abstract
Reinforcement learning (RL) has made substantial empirical progress in solving hard AI challenges in the past few years. A large fraction of these progresses—Go, Dota 2, Starcraft 2, economic simulation, social behavior learning, and so on—come from multi-agent RL, that is, sequential decision making involving more than one agent. While the theoretical study of single-agent RL has a long history and a vastly growing recent interest, Multi-Agent RL (MARL) theory is arguably a newer and less developed field. In this talk, I will present our recent theoretical developments in MARL theory. Starting with basic formulations, we present several provably efficient algorithms for finding equilibria in MARL problems, addressing unique challenges in MARL such as the curse of multiagents and the design of decentralized algorithms.
Bio
Chi Jin is an assistant professor at the Electrical and Computer Engineering department of Princeton University. He obtained his PhD degree in Computer Science at the University of California, Berkeley, advised by Michael I. Jordan. His research mainly focuses on theoretical machine learning, with special emphasis on nonconvex optimization and reinforcement learning. His representative work includes proving noisy gradient descent escape saddle points efficiently and proving the efficiency of Q-learning and least-squares value iteration when combined with optimism in reinforcement learning.
