Apr 12, 2024 Friday
Abstract:
Deep reinforcement learning combines the perceptual capabilities of deep learning with the decision-making prowess of reinforcement learning, allowing intelligent agents to execute various action decisions directly based on input environmental information. This represents an artificial intelligence algorithm that more closely mirrors human cognitive processes. In recent years, deep reinforcement learning has found broad application in domains such as intelligent gaming, financial risk control, and infectious disease prevention and control. For instance, in 2016, AlphaGo, which is based on a reinforcement learning algorithm framework, defeated the world champion of Go, heralding a new wave of technological transformation from theoretical research to practical application in artificial intelligence. This report will present the recent research findings of our group in the frontier technologies and practical applications of deep reinforcement learning.
Time:
Apr 12, 2024 Friday
11:00-11:50
Location:
Rm W1-101, GZ Campus
Online Zoom
Join Zoom at: https://hkust-gz-edu-cn.zoom.us/j/4236852791 OR 423 685 2791
Speaker Bio:
Prof. Hechang CHEN 陈贺昌
Associate Professor, School of Artificial Intelligence, Jilin University (JLU)
Hechang Chen is an associate professor at the School of Artificial Intelligence, Jilin University (JLU), China, and deputy director of the Engineering Research Center of Knowledge-Driven Human-Machine Intelligence, Ministry of Education, China. He received his Ph.D. from the College of Computer Science and Technology, Jilin University (JLU), in December 2018. He enrolled at the University of Illinois at Chicago (UIC) as a joint training Ph.D. student from November 2015 to December 2016 and at Hong Kong Baptist University (HKBU) as a visiting Ph.D. student from July 2017 to January 2018. He has published over 60 articles in international conferences and journals, including IEEE TPAMI, TKDE, TIST, TNNLS, TKDD, NeurIPS, AAAI, IJCAI, SIGIR, ICDE, WWW, etc. His research interests include machine learning, data mining, reinforcement learning, complex systems, and knowledge engineering.