报 告 人：Bo Dai
主 持 人：王奕森 助理教授
必赢71886网址登录智能学院
时 间：2024年 4月10日周三 14:00 - 15:00
地 址：燕园校区理科二号楼2736报告厅
新燕园校区教学楼101教室
腾讯会议：938-779-290
报告题目：
报告摘要:
The majority reinforcement learning (RL) algorithms are largely categorized as model-free and model-based through whether a world model is learned in the algorithm. However, both of these two categories have their own issues, especially incorporating with function approximation: the exploration with arbitrary function approximation in model-free RL algorithms is difficult, while optimal planning becomes intractable in model-based RL algorithms with neural nonlinear world models.
In this talk, I will present our recent work on exploiting the power of representation in RL to bypass these difficulties, while enjoys best of both worlds. Specifically, we designed practical algorithms for extracting useful representations from world model, with the goal of improving statistical and computational efficiency in exploration vs. exploitation tradeoff and empirical performance in RL. We provide rigorous theoretical analysis of our algorithm, and demonstrate the practical superior performance over the existing state-of-the-art empirical algorithms on several benchmarks.
报告人简介:
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 Embodied Ai with Generative Models. He is the recipient of the best paper award of AISTATS and NeurIPS workshop. He regularly serves as area chair or senior program committee member at major AI/ML conferences such as ICML, NeurIPS, AISTATS, and ICLR.
