短期课程

题目：强化学习

报告人：史成春 （伦敦政经学院）

摘要：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 rewad 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, containing  

1. Foundations of RL;

2. Planning and learning;

3. Q-learning and beyond;

4. Off-policy evaluation.

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

报告人简介：

Chengchun is an Associate Professor in the Department of Statistics at LSE. He works at the interface of RL, LLMs and statistics, with applications to ride-sharing and healthcare. His work brings to light the relevance and significance of statistical learning in RL, and demonstrates the usefulness of RL as a framework for policy evaluation and A/B testing in two-sided marketplaces. Chengchun has published over 50 papers, with majority of them accepted in prestigious statistical journals (JRSSB, JASA, AoS) and top machine learning venues (NeurIPS, ICML, KDD, JMLR). His outstanding contributions have been recognized with esteemed awards such as the Peter Gavin Hall IMS Early Career Prize, IMS Tweedie Award and the Royal Statistical Society Research Prize. He is serving as the associate editors of prestigious journals JRSSB, JASA and AoAS.

报告时间:

2025年7月23日 2:00 – 4:30 ； 2025年7月25日 2:00 – 4:30 ；

2025年7月28日 2:00 - 4:30；2025年7月30日2:00 – 4:30  

报告地点：教二楼610

联系人：胡涛