Zhi Wang
 |
Associate Professor, Nanjing University 22 Hankou Road, Gulou District, Nanjing, China Reinforcement Learning, In-context RL, Language-conditioned RL, Embodied AI
|
About me
I am now an Associate Professor in Nanjing University. I received the Ph.D. degree (Advisor: Professor Han-Xiong Li) from City University of Hong Kong and the bachelor's degree from Nanjing University. I was a visiting scholar at University of New South Wales (Visiting Advisor: Professor Daoyi Dong) and Institute of Automation, Chinese Academy of Sciences (Visiting Advisors: Professor Yuanheng Zhu, Dongbin Zhao).
My research interests include reinforcement learning (RL) algorithms and their applications on robot learning.
Specifically, I work on how learning algorithms can scale RL agents to (i) dynamic environments, (ii) offline settings, and (iii) multi-agent systems, allowing them to autonomously adapt to (i) non-stationary task distributions, (ii) non-interactive scenarios, and (iii) cooperative or competitive task assignments in real-world domains.
This includes a wide range of topics such as (i) in-context RL, meta-RL, lifelong/continual RL, (ii) offline RL, large models for RL, and (iii) multi-agent RL.
My current research focuses on the prominent advancements in AI, particularly in transformer architectures and self-supervised learning algorithms, with the goal of advancing large models, the scaling law, and AIGC ideas in the field of RL .
Academic Services
Associate Editor
Special Sessions, IEEE International Conference on Systems, Man, and Cybernetics (SMC), 2023, 2022, & 2021
Special Sessions, IEEE International Conference on Networking, Sensing, and Control (ICNSC), 2020
Reviewer
Journals: IEEE TPAMI, TNNLS, IEEE TCYB, IEEE TSYS, IEEE-ASME TMECH, IEEE-CAA JAS
Conferences: ICLR, NIPS, CVPR, AAAI, ECAI
Invited Talks
The 4th Conference on Distributed Artificial Intelligence (DAI), Lifelong reinforcement learning for dynamic environments, 2022.12
Institute of Automation, Chinese Academy of Sciences, Lifelong reinforcement learning for dynamic environments, 2022.12
Tongji University, Lifelong reinforcement learning for dynamic environments, 2022.12
University of Science and Technology of China, <Deep Reinforcement Learning>, Summer Course, Instructor, 2022.07
University of Electronic Science and Technology of China, Incremental reinforcement learning for dynamic environments, 2020.12
University of Science and Technology of China, Incremental reinforcement learning for dynamic environments, 2020.12
University of New South Wales, Incremental reinforcement learning for dynamic environments, 2019.04
Teaching
<Deep Reinforcement Learning>, for postgraduates
<Digital Circuits>, for undergraduates
Research Grants
Open-Environment Lifelong Reinforcement Learning: Methods and Applications, General Program of the National Natural Science Foundation of China
Incremental Reinforcement Learning for Fast Adaptation to Dynamic Environments: Theories, Algorithms, and Applications, Youth Program of the National Natural Science Foundation of China
Honors and Awards
Youth Science and Technology Talent Support Project, Jiangsu Province, 2024
Zijin Scholar, Nanjing University, 2024
Youth Science and Technology Award, Jiangsu Automation Society, 2023
Doctor of Innovation and Entrepreneurship, Jiangsu Province, 2020
Outstanding Academic Performance Award, City University of Hong Kong, 2018
Research Tuition Scholarship, City University of HongKong, 2018