Regaining in Reinforcement Learning

Principal Investigator: Benjamin Van Roy (Stanford)

Co-PI: Sean Meyn

Sponsor: Army Research Office

Start Date: May 1, 2019

End Date: April 30, 2022

Amount: $108,453

Abstract

This proposal was written to support a postdoctoral fellowship for UF graduate Adithya Devraj, and to support collaboration between the two PIs.  
 

Along with the sharp increase in visibility of the field, the rate at which new reinforcement learning algorithms are being proposed is at a new peak. While the surge in activity is creating more excitement, there seems to be a gap in understanding of fundamental principles that these algorithms need to satisfy for any meaningful applications. The goal of this project is to address these gaps via two orthogonal approaches:   design of more efficient algorithms for learning,  and development of scalable exploration techniques that can lead to efficient learning.