统计学国家重点学科(2007)

【光华讲坛】Reinforcement Learning 强化学习(二)
2024-10-22

主题Reinforcement Learning 强化学习(二)

主讲人伦敦政治经济学院 史成春副教授

主持人西南财经大学36365路检测中心-官网(36365路检测中心) 常晋源教授

2024年11月05日(周二)上午09:00-12:00

举办地点:西南财经大学光华校区光华楼1003会议室

主办单位:数据科学与商业智能联合实验室 36365路检测中心-官网(36365路检测中心) 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 (TM), JASA (CS) and Journal of Nonparametric Statistics. His research focuses on developing statistical learning methods in reinforcement 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

史成春是伦敦经济学院和政治科学学院的副教授。他目前担任《皇家统计学会B期刊》(JRSSB)、《美国统计协会期刊》(JASA,技术与方法版)、《美国统计协会期刊》(JASA,计算科学版)和《非参数统计杂志》的副主编。他的研究重点是开发强化学习中的统计学习方法,并将其应用于医疗保健、拼车、视频分享和神经成像等领域。他曾于2021年获得皇家统计学会研究奖,并在2024年获得了IMS Tweedie奖。

内容简介

Reinforcement learning (RL, see Sutton and Barto, 2018, for an overview) is a powerful machine learning technique that allows an agent to learn and interact with a given environment, to maximize the cumulative reward the agent receives. It has been one of the most popular research topics in the machine learning and computer science literature over the past few years. Significant progress has been made in solving challenging problems across various domains using RL, including games, recommender systems, finance, healthcare, robotics, transportation. This course covers basics of RL. It contains three lectures, including

1. Foundations of Reinforcement Learning

2. Planning and Learning

3. Q-Learning and Beyond

We will also provide code to implement various RL algorithms discussed in the lecture. The materials of this course is available on https://github.com/callmespring/RL-short-course.

强化学习(RL,见 Sutton 和 Barto,2018的概述)是一种强大的机器学习技术,它允许一个代理学习并与给定的环境互动,以最大化代理收到的累积奖励。在过去几年中,它一直是机器学习和计算机科学文献中最流行的研究主题之一。在各种领域使用 RL 解决挑战性问题方面取得了显著进展,包括游戏、推荐系统、金融、医疗保健、机器人技术和交通。这个课程涵盖了 RL 的基础知识。它包含三个讲座,包括:

1. 强化学习的基础

2. 规划与学习

3. Q-学习及其超越

我们还将提供代码来实现讲座中讨论的各种 RL 算法。这个课程的材料可以在https://github.com/callmespring/RL-short-course上找到。