Monday, February 22, 2021 - 11:30am to 12:30pm
Event Calendar Category
CSAIL
Speaker Name
Akshay Krishnamurthy
Affiliation
Microsoft Research
Join Zoom meeting
https://mit.zoom.us/j/94665448181
Abstract
We will discuss new provably efficient algorithms for reinforcement in rich observation environments with arbitrarily large state spaces. These 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. The second algorithm, called FLAMBE, operates in a much richer class of low-rank MDPs and is model-based. Finally, Moffle is a model-free representation learning approach for low-rank MDPS. All algorithms accommodate nonlinear function approximation and enjoy the provable sample and computational efficiency guarantees.
Biography
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.