3월 23일(수) 수요 세미나 안내

3월 23일(수) 수요 세미나 안내입니다.

Zoom 출결 로그로 출석을 확인할 계획이니 반드시 표시되는 이름을 본인의 실명으로 설정하고, 가급적 제출한 계정으로 로그인하여 Zoom에 접속하여 주시기 바랍니다.

제목: Unsupervised Skill Discovery
강사: 김건희 교수 (서울대학교 컴퓨터공학부)
일시: 2021년 3월 23일 (수요일) 오후 5시
Zoom 회의 참가 :
https://yonsei.zoom.us/j/9729804081
회의 ID: 972 980 4081
SIP로 참가
9729804081@zoomcrc.com
H.323으로 참가
162.255.37.11 (미국 서부)
162.255.36.11 (미국 동부)
115.114.131.7 (인도 뭄바이)
115.114.115.7 (인도 하이데라바드)
213.19.144.110 (네덜란드 암스테르담)
213.244.140.110 (독일)
103.122.166.55 (호주 시드니)
103.122.167.55 (호주 멜버른)
209.9.211.110 (홍콩 특별 행정구)
64.211.144.160 (브라질)
69.174.57.160 (캐나다 토론토)
65.39.152.160 (캐나다 밴쿠버)
207.226.132.110 (일본 도쿄)
149.137.24.110 (일본 오사카)
회의 ID: 972 980 4081

Abstract: In this talk, I will present some of our recent works for unsupervised skill discovery in reinforcement learning, whose goal is to teach agents to acquire inherent skills from environments without any external rewards or supervision. First, I deal with how to make policy gradient (PG) methods invariant to time discretization for control. Second, I propose a novel unsupervised skill discovery method named Information Bottleneck Option Learning (IBOL) that leverages the information bottleneck principle from representation learning. Finally, I discuss Lipschitz-constrained Skill Discovery (LSD), which encourages the agent to discover more diverse, dynamic, and far-reaching skills than previous unsupervised skill discovery methods. All these works are recently published in ICML 2021, NeurIPS 2021 and ICLR 2022.

Bio: Gunhee Kim is an associate professor in the Department of Computer Science and Engineering of Seoul National University from 2015. He was a postdoctoral researcher with Leonid Sigal at Disney Research for one and a half years. He received his PhD in 2013 under supervision of Eric P. Xing from Computer Science Department of Carnegie Mellon University. Prior to starting PhD study in 2009, he earned a master’s degree under supervision of Martial Hebert in Robotics Institute, CMU. His research interests are solving computer vision and web mining problems that emerge from big image data shared online, by developing scalable and effective machine learning and optimization techniques. He is a recipient of 2014 ACM SIGKDD doctoral dissertation award, 2015 Naver New faculty award, and Best Full Paper Runner-up at ACM VRST 2019. Please visit his website for more details: https://vision.snu.ac.kr/gunhee/ .