About Speakers Schedule INS
2024年人工智能与计算数学会议
Artificial Intelligence and Computational Mathematics Conference

Recent Progress on the Convergence of Policy Gradient Methods

Speaker

魏轲 Ke Wei , 复旦大学 Fudan University

Time

16 Mar, 09:15 - 09:45

Abstract

Reinforcement learning (RL) is a type of machine learning technique for solving sequential decision problems which has achieved great success in many areas. Some recent progress on the convergence of exact policy gradient methods for RL will be discussed in this talk, with an emphasis on the convergence of projected policy gradient method, and the convergence of other methods will be briefly mentioned if time permitted.