Invited Speeches

Invited Speech I

Reinforcement Learning Assisted Large Models and Embodied Intelligence

Dongbin Zhao
Institute of Automation, Chinese Academy of Sciences
University of Chinese Academy of Sciences

Large models and embodied intelligence are hot directions in the field of artificial intelligence, where reinforcement learning methods play a significant role in their development. This report first introduces the basic concepts and scope of reinforcement learning, then elaborates on its supporting role in the development of large models and embodied intelligence, and finally shares the research work of the team in applying related methods to the fields of robotics and autonomous driving.

Biosketch

Dongbin Zhao is a professor with the Institute of Automation, Chinese Academy of Sciences, and the University of Chinese Academy of Sciences, China. Dr. Zhao serves as several Associate Editors, including IEEE Transactions on Systems, Man and Cybernetics: Systems, and IEEE Transactions on Artificial Intelligence. He is involved in organizing many international conferences, including General Chair of IEEE Conference on Games 2022. He has published 9 books, and over 300 international journal and conference papers, including the Outstanding/Best Paper Award of IEEE TASE, TETCI, and TCDS. His current research interests lie in deep reinforcement learning, large models and embodied intelligence, smart driving, game artificial intelligence, robotics, etc. He is an IEEE Fellow.