Abstract:

Reinforcement learning (RL) has become a prominent branch of artificial intelligence, achieving remarkable success in various domains, including Chinese Go, computer games, robotics, large language models, and autonomous driving.

This tutorial lecture provides a comprehensive introduction to RL's fundamental theories, algorithm design methods and key applications. It also covers some critical issues, including how to handle safety constraints in real-world applications, and how to mitigate issues like non-iid sequential data, easy to divergence, overestimation, and sample inefficiency.

Three recent algorithm advancements in RL are also introduced, including: (1) distributional soft actor-critic (DSAC) algorithm, which mitigates value overestimation and achieves state-of-the-art policy performance; (2) relativistic adaptive gradient descent (RAD) method, which preserves symplecticity in RL dynamic systems and ensures long-term training stability; and (3) general optimal control problem solver (GOPS), an easy-to-use RL solver package designed for building real-time, high-performance controllers in industrial control field.

Bio:

Shengbo Eben Li received his M.S. and Ph.D. degrees from Tsinghua University in 2006 and 2009. He has worked at Stanford University, University of Michigan, and UC Berkeley. He is currently a full professor at Tsinghua University, as the leader of Intelligent Driving Lab (iDLab). His active research interests include intelligent vehicles and driver assistance, deep reinforcement learning, optimal control and estimation, etc. He is the author of over 190 peer-reviewed journal/conference papers, and co-inventor of over 40 patents. Dr. Li has received over 20 prestigious awards, including Youth Sci. & Tech Award of Ministry of Education (annually 10 receivers in China), Natural Science Award of Chinese Association of Automation (First level), National Award for Progress in Sci & Tech of China, and best (student) paper awards of IET ITS, IEEE ITS, IEEE ICUS, CVCI, etc. He also serves as Board of Governor of IEEE ITS Society, Senior AE of IEEE OJ ITS, and AEs of IEEE ITSM, IEEE TITS, IEEE TIV, IEEE TNNLS, etc.