主题：Efficient Reinforcement Learning Through Uncertainties

报告人：Dongruo ZHOU, Final-year Ph.D. student, Department of Computer Science, UCLA

主持人：Tianshu YU, Assistant Professor, School of Data Science, CUHK-Shenzhen

日期：12 April (Wednesday), 2023

时间：12:00 to 13:00, Beijing Time

形式：Hybrid

线下地点：103 Meeting Room, Daoyuan Building

Zoom链接：https://cuhk-edu-cn.zoom.us/j/5304767369?pwd=aFErUGFSSDlLNWJld0VNNmpTL0k0UT09

Zoom会议号：5304767369

密码：852648

语言：English

摘要：

Reinforcement learning (RL) has achieved great empirical success in many real-world problems in the last few years. However, many RL algorithms are inefficient due to their data-hungry nature. Whether there exists a universal way to improve the efficiency of existing RL algorithms remains an open question.

In this talk, I will give a selective overview of my research, which suggests that efficient (and optimal) RL can be built through the lens of uncertainties. I will show that uncertainties can not only guide RL to make decisions efficiently, but also have the ability to accelerate the learning of the optimal policy over a finite number of data samples collected from the unknown environment. By utilizing the proposed uncertainty-based framework, I design computationally efficient and statistically optimal RL algorithms under various settings, which improve existing baseline algorithms from both theoretical and empirical aspects.

简介：

Dongruo Zhou is a final-year Ph.D. student in the Department of Computer Science at UCLA, advised by Prof. Quanquan Gu. His research is broadly on the foundation of machine learning, with a particular focus on reinforcement learning and stochastic optimization. He aims to provide a theoretical understanding of machine learning methods, as well as to develop new machine learning algorithms with better performance. He is a recipient of the UCLA dissertation year fellowship.