报告摘要：Deep reinforcement learning (DRL) is a combination of reinforcement learning (RL) and deep learning. This field of research has been able to solve a wide range of complex decision-making tasks that were previously out of reach for a machine. Thus, DRL opens up many new applications in domains such as video games, healthcare, robotics, smart grids, finance, and many more. In this talk, I will show you the application of DRL in wireless networking and beyond.
Imagine a wireless medium-access control (MAC) protocol that can learn the best strategy to exploit the time-spectrum resources. It can co-exist harmoniously with a mix of different legacy wireless networks, such as cellular networks, Wi-Fi and ZigBee. Furthermore, it can achieve optimal performance without knowing the details of the MAC protocols of the other networks – i.e., it does not need to know the operating principles of other co-existing MAC protocols; yet it can achieve optimal performance as if it knew how these protocols work. Such a “universal MAC protocol” does not exist today. I will try to convince you that DRL may hold the key to such universal MAC protocols through this talk. We conclude this talk by sharing some tips on DRL.
报告人简介：Yiding Yu received the B.E. degree in communication engineering and the B.B.A degree in business administration from the University of Electronic Science and Technology of China (UESTC) in 2016. He is currently pursuing a Ph.D. degree with the Department of Information Engineering, The Chinese University of Hong Kong (CUHK). He will be a visiting student of Massachusetts Institute of Technology (MIT) from Sept. 2019 to Feb. 2020. His research interests include deep reinforcement learning, wireless communications and networking. He has served as technique reviewer of IEEE Journal of Selected Areas on Communications (JSAC), IEEE Trans. on Vehicular Technology (TVT), and IEEE Access. Yiding Yu is a recipient of the Postgraduate Studentship (2016-2020), Overseas Research Attachment Programme Award (2018-2019), and Global Scholarship Programme for Research Excellence (2019-2020) of CUHK.
© 2018 厦门大学 信息科学与技术学院 版权所有