“Reward free Reinforcement Learning via Sample Efficient Representation Learning”
Friday, March 10 at 1:00pm
Location: LAR 234
Join via Zoom
As reward-free reinforcement learning (RL) becomes a powerful framework for a variety of multi-objective applications, representation learning arises as an effective technique to deal with the curse of dimensionality in reward-free RL. However, the existing algorithms of representation learning in reward-free RL still suffers seriously from high sample complexity, although they are polynomially efficient. In this talk, I will first present a novel representation learning algorithm that we propose for reward-free RL. We show that such an algorithm provably finds near-optimal policy as well as attaining near-accurate system identification via reward-free exploration, with significantly improved sample complexity compared to the best-known result before. I will then present our characterization of the benefit of representation learning in reward-free multitask (a.k.a. meta) RL as well as the benefit of employing the learned representation from upstream to downstream tasks. I will conclude my talk with remarks of future directions.
Dr. Yingbin Liang is currently a professor at the Department of Electrical and Computer Engineering at the Ohio State University (OSU), and a core faculty of the Ohio State Translational Data Analytics Institute (TDAI). She also serves as the Deputy Director of the AI-Edge Institute at OSU. Dr. Liang received the Ph.D. degree in Electrical Engineering from the University of Illinois at Urbana-Champaign in 2005, and served on the faculty of University of Hawaii and Syracuse University before she joined OSU. Dr. Liang’s research interests include machine learning, optimization, information theory, and statistical signal processing. Dr. Liang received the National Science Foundation CAREER Award and the State of Hawaii Governor Innovation Award in 2009. She also received EURASIP Best Paper Award in 2014.