IFML Seminar: 10/25/24 - Representation-based Reinforcement Learning

Abstract: Reinforcement learning often faces a trade-off between model flexibility and computational tractability. Flexible models can capture complex dynamics and policy but often introduce nonlinearity, making planning and exploration challenging. In this talk, we explore how representation learning can help overcome this dilemma. We present algorithms that extract flexible representations, which enabling practical and provable planning and exploration. We provide theoretical guarantees our algorithm for RL in MDP and POMDP settings, and empirical results demonstrating the superiority of our approach on various benchmarks.

Personal Bio: Bo Dai is an assistant professor in Georgia Tech and a staff research scientist in Google DeepMind. He obtained his Ph.D. from Georgia Tech. His research interest lies in developing principled and practical algorithms for reinforcement learning and generative models. He regularly serves as area chair or senior program committee member at major AI/ML conferences such as ICML, NeurIPS, AISTATS, and ICLR.