날짜 : 2023년 11월 1일(수) 15:00~17:00
장소 : 제4공학관 D508호

Title: A Gentle Introduction to Reinforcement Learning and Robot Learning

Abstract:

With rapid progress in deep learning research, models like AlphaGo, ChatGPT, and StableDiffusion have surprised us with their human-like capabilities in games, conversations, image generation, and more. How do these AI systems attain such impressive skills? Training these deep learning models only from human-collected data is not enough to achieve (super)human-level performance. In this talk, I will first provide a gentle introduction to Reinforcement Learning (RL), which empowers machines to outperform humans in various tasks. Then, we will explore the potential of deep reinforcement learning in robotics and discuss why robots haven’t shown human-like intelligence with deep learning yet. Lastly, I will briefly talk about interesting research topics in my future lab.

Bio:

Youngwoon Lee is an incoming assistant professor in AI at Yonsei University and currently a postdoctoral scholar at the University of California, Berkeley working with Prof. Pieter Abbeel. Prior to joining UC Berkeley, he received his Ph.D. in Computer Science at the University of Southern California in 2022, advised by Prof. Joseph J. Lim, and received his B.S. and M.S. degrees in Computer Science at KAIST. His research interests are in deep reinforcement learning and imitation learning for robotics. Particularly, his research focuses on solving complex long-horizon tasks, such as furniture assembly, which requires many aspects of intelligent robots from structural reasoning to long-term planning to sophisticated control. Youngwoon’s research has been recognized with the Best System Paper Award at RSS’23 and the Best Paper Presentation Award at CoRL’20.