快来参与最新一期的理论中心前沿系列讲座吧！往期精彩回顾也为你整理好了哦！

微软亚洲研究院理论中心前沿系列讲座第七期，将于12月22日（本周四）上午10:00-11:00与你相见！这一期，我们邀请到了俄亥俄州立大学电气与计算机工程系教授 Yingbin Liang ，带来以 “通过样本高效的表示学习进行无奖励强化学习” 为主题的讲座分享，届时请锁定 B 站 “微软中国视频中心” 直播间！

错过了此前的直播？不必担心！今天我们还为大家整理了四至六期的讲座回顾，速戳下文了解详细信息吧！

扫码或点击 “阅读原文” 直达直播间

Yingbin Liang

俄亥俄州立大学

电气与计算机工程系教授

Dr. Yingbin Liang is currently a Professor at the Department of Electrical and Computer Engineering at the Ohio State University (OSU), and a core faculty of the Ohio State Translational Data Analytics Institute (TDAI). She also serves as the Deputy Director of the AI-Edge Institute at OSU. Dr. Liang received the Ph.D. degree in Electrical Engineering from the University of Illinois at Urbana-Champaign in 2005, and served on the faculty of University of Hawaii and Syracuse University before she joined OSU. Dr. Liang's research interests include machine learning, optimization, information theory, and statistical signal processing. Dr. Liang received the National Science Foundation CAREER Award and the State of Hawaii Governor Innovation Award in 2009. She also received EURASIP Best Paper Award in 2014.

报告题目:   

Reward-free Reinforcement Learning via Sample-Efficient Representation Learning

通过样本高效的表示学习进行无奖励强化学习

报告摘要: 

As reward-free reinforcement learning (RL) becomes a powerful framework for a variety of multi-objective applications, representation learning arises as an effective technique to deal with the curse of dimensionality in reward-free RL. However, the existing algorithms of representation learning in reward-free RL still suffers seriously from high sample complexity, although they are polynomially efficient. In this talk, I will first present a novel representation learning algorithm that we propose for reward-free RL. We show that such an algorithm provably finds near-optimal policy as well as attaining near-accurate system identification via reward-free exploration, with significantly improved sample complexity compared to the best-known result before. I will then present our characterization of the benefit of representation learning in reward-free multitask (a.k.a. meta) RL as well as the benefit of employing the learned representation from upstream to downstream tasks. I will conclude my talk with remarks of future directions.

The work to be presented was jointly with Yuan Cheng (USTC), Ruiquan Huang (PSU), Dr. Songtao Feng (OSU), Prof. Jing Yang (PSU), and Prof. Hong Zhang (USTC).

张景昭

清华交叉信息研究院助理教授

张景昭现任清华交叉信息研究院助理教授，博士毕业于麻省理工学院计算机科学专业，曾获伯克利研究生奖学金，MIT Lim 奖学金，IIIS 青年学者奖学金等奖项。研究主要包含优化算法复杂性分析，机器学习理论，以及人工智能应用。

回放地址：

https://www.bilibili.com/video/BV19N4y1N7UE/

苏炜杰

宾夕法尼亚大学

统计与数据科学系副教授

苏炜杰现任宾夕法尼亚大学沃顿商学院统计与数据科学系以及工学院计算机系副教授，同时他也是宾大机器学习研究中心的联合主任。2016年，他博士毕业于斯坦福大学，2011年本科毕业于北京大学。苏教授的主要研究方向为隐私数据保护、深度学习理论、最优化理论、高维数据推断和机制设计。他曾获得斯坦福 Theodore Anderson 毕业论文奖(2016)、NSF CAREER Award (2019)、斯隆研究奖(2020)、美国工业与应用数学学会（SIAM）数据科学青年奖（2022）和 IMS Peter Gavin Hall Prize（2022）。

回放地址：

https://www.bilibili.com/video/BV1vg411a7ra

李帅

上海交通大学约翰·霍普克罗夫特

计算机科学中心助理教授

欢迎扫码加入理论研究社区，与关注理论研究的研究者交流碰撞，群内也将分享微软亚洲研究院理论中心前沿系列讲座的最新信息。你也可以向 [email protected] 发送以 "Subscribe the Lecture Series" 为主题的邮件订阅讲座信息。

微信群二维码

你也许还想看：