ABSTRACT:

I will discuss new provably efficient algorithms for reinforcement in rich observation environments with arbitrarily large state spaces. Both algorithms operate by learning succinct representations of the environment, which they use in an exploration module to acquire new information. The first algorithm, called Homer, operates in a block MDP model and uses a contrastive learning objective to learn the representation. On the other hand, the second algorithm, called FLAMBE, operates in a much richer class of low rank MDPs and is model based. Both algorithms accommodate nonlinear function approximation and enjoy provable sample and computational efficiency guarantees.

BIO:

Akshay Krishnamurthy is a principal researcher at Microsoft Research, New York City. Previously, he spent two years as an assistant professor in the College of Information and Computer Sciences at the University of Massachusetts, Amherst and a year as a postdoctoral researcher at Microsoft Research, NYC. He completed his PhD in the Computer Science Department at Carnegie Mellon University, advised by Aarti Singh. His research interests are broadly in machine learning and statistics. More specifically, he is most excited about interactive learning, or learning settings that involve feedback-driven data collection. Recently his work has focused on decision making problems with limited feedback, including contextual bandits and reinforcement learning.

Hosted by Professor Quanquan Gu

Via: Zoom Webinar