报告题目：Recent advances in Distributional Reinforcement Learning

报告时间：2023-12-18 14:00-15:00

报 告 人 ：周帆  副教授  上海财经大学

报告地点：理学院东北楼一楼报告厅（110）

Abstract：Although distributional reinforcement learning (DRL) has been widely examined in the past few years, very few studies investigate the validity of the obtained Q-function estimator in the distributional setting. In this talk, we discuss the most recent advances in DRL and some of our works in exploring the accuracy of the obtained return estimation.