{"id":39974,"date":"2023-12-03T21:59:30","date_gmt":"2023-12-04T02:59:30","guid":{"rendered":"https:\/\/www.bu.edu\/cise\/?page_id=39974"},"modified":"2024-01-16T13:06:46","modified_gmt":"2024-01-16T18:06:46","slug":"cise-seminar-xuezhou-zhang","status":"publish","type":"page","link":"https:\/\/www.bu.edu\/cise\/cise-seminar-xuezhou-zhang\/","title":{"rendered":"CISE Seminar: Xuezhou Zhang, Boston University"},"content":{"rendered":"

Date: Friday, February 2, 2024
\nTime: 3:00pm – 4:00pm
\nLocation: 8 Saint Mary’s Street, PHO 203<\/p>\n

\"\"
Assistant Professor Xuezhou Zhang, Boston University<\/figcaption><\/figure>\n

Xuezhou Zhang<\/span><\/strong>
\nAssistant Professor<\/span>
\n Boston University<\/span><\/h4>\n

Representation Learning for Efficient RL<\/strong><\/span>
\nReinforcement Learning (RL) has been considered a promising paradigm to solve decision making tasks. However, over the past years, RL has only found limited successes in applications with high quality data or a near-perfect simulator at disposal. The main drawback of existing RL algorithms is their poor sample complexity, i.e. it takes too many trials and errors to learn a good policy. In this talk, I will discuss recent attempts to solve this problem through the paradigm of representation learning, which aims to learn low-dimensional embedding of the observation and perform efficient RL in the embedding space instead of the raw observation space. This approach has achieved up to 1000x improvement in sample complexity over existing methods on the Atari Game benchmarks.<\/span><\/p>\n

Xuezhou Zhang<\/strong><\/a> is a tenured track assistant professor in the Faculty of Computing and Data Sciences (CDS) at Boston University. Previously, he spent two years at Princeton University as a postdoctoral associate. Before that, he\u00a0obtained his Ph.D. of Computer Sciences in 2021 from the University of Wisconsin-Madison, advised by Jerry Zhu. His research interests include reinforcement learning, trustworthy ML and developing\u00a0ML tools for nature sciences.<\/span><\/div>\n

 <\/p>\n

Faculty Host:<\/strong> Alex Olshevsky<\/span><\/a>
\nStudent Host:<\/strong> Mehdi Kermanshah<\/span><\/a><\/p>\n","protected":false},"excerpt":{"rendered":"

Date: Friday, February 2, 2024 Time: 3:00pm – 4:00pm Location: 8 Saint Mary’s Street, PHO 203 Xuezhou Zhang Assistant Professor Boston University Representation Learning for Efficient RL Reinforcement Learning (RL) has been considered a promising paradigm to solve decision making tasks. However, over the past years, RL has only found limited successes in applications with […]<\/p>\n","protected":false},"author":22390,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":[],"_links":{"self":[{"href":"https:\/\/www.bu.edu\/cise\/wp-json\/wp\/v2\/pages\/39974"}],"collection":[{"href":"https:\/\/www.bu.edu\/cise\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/www.bu.edu\/cise\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/www.bu.edu\/cise\/wp-json\/wp\/v2\/users\/22390"}],"replies":[{"embeddable":true,"href":"https:\/\/www.bu.edu\/cise\/wp-json\/wp\/v2\/comments?post=39974"}],"version-history":[{"count":28,"href":"https:\/\/www.bu.edu\/cise\/wp-json\/wp\/v2\/pages\/39974\/revisions"}],"predecessor-version":[{"id":40341,"href":"https:\/\/www.bu.edu\/cise\/wp-json\/wp\/v2\/pages\/39974\/revisions\/40341"}],"wp:attachment":[{"href":"https:\/\/www.bu.edu\/cise\/wp-json\/wp\/v2\/media?parent=39974"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}