主 题：Statistical Inference in Reinforcement Learning强化学习中的统计推断

主讲人：伦敦政治经济学院史成春副教授

主持人：统计学院林华珍教授

时间：2024年11月5日（周二）下午4：00-5：00

线下地点：柳林校区弘远楼408会议室

线上会议号：腾讯会议 502-404-442

主办单位：统计研究中心和统计学院 科研处

主讲人简介：

Chengchun Shi is an Associate Professor at London School of Eco- nomics and Political Science. He is serving as the associate editors of JRSSB, JASA and Journal of Nonparametric Statistics. His research focuses on developing statistical learning methods in rein- forcement learning, with applications to healthcare, ridesharing, video-sharing and neuroimaging. He was the recipient of the Royal Statistical Society Research Prize in 2021 and IMS Tweedie Award in 2024.

史成春，伦敦政治经济学院副教授。他目前担任JRSSB , JASA 和 Journal of Nonparametric Statistics的副主编。他的研究专注于发展强化学习中的统计学习方法，并将其应用于医疗、拼车、视频共享和神经成像等领域。他于2021年获得英国皇家统计学会（RSS）Research Prize，并于2024年获得IMS Tweedie奖。

内容简介：

Reinforcement learning (RL) is concerned with how intelligence agents take actions in a given environment to maximize the cumulative reward they receive. In healthcare, applying RL algorithms could assist patients in improving their health status. In ride-sharing platforms, applying RL algorithms could increase drivers' income and customer satisfaction. RL has been arguably one of the most vibrant research frontiers in machine learning over the last few years. Nevertheless, statistics as a field, as opposed to computer science, has only recently begun to engage with reinforcement learning both in depth and in breadth. In this talk, I will discuss some of my recent work on developing statistical inferential tools for reinforcement learning, with applications to mobile health and ride-sharing companies. The talk will cover several different papers published in highly-ranked statistical journals (JASA & JRSS-B) and top machine learning conferences (ICML & NeurIPS).

强化学习（RL）关注的是智能代理在给定环境中如何采取行动以最大化其累计奖励。在医疗领域，应用RL算法可以帮助患者改善健康状况。在打车平台上，应用RL算法可以增加司机的收入和客户满意度。在过去的几年里，RL可以说是机器学习领域最活跃的研究前沿之一。然而，与计算机科学不同，统计学作为一门学科，才刚刚开始在深度和广度上与强化学习进行互动。在这次演讲中，主讲人将讨论我在开发用于强化学习的统计推断工具方面的一些最新工作，这些工具已在移动健康和打车公司中得到应用。演讲将涵盖发表在顶级统计期刊（JASA与JRSS-B）和顶级机器学习会议（ICML与NeurIPS）上的多篇论文。