26 citations · 40 across the 9 of their papers we have counts for
4 papers · 1 filter
Policy Mirror Descent Inherently Explores Action Space
Yan Li, Guanghui Lan
Explicit exploration in the action space was assumed to be indispensable for online policy gradient methods to avoid a drastic degradation in sample complexity, for solving general…
CRPO: A New Approach for Safe Reinforcement Learning with Convergence Guarantee
Tengyu Xu, Yingbin Liang, Guanghui Lan
In safe reinforcement learning (SRL) problems, an agent explores the environment to maximize an expected total reward and meanwhile avoids violation of certain constraints on a num…
GLAD: Learning Sparse Graph Recovery
Harsh Shrivastava, Xinshi Chen, Binghong Chen +4
Recovering sparse conditional independence graphs from data is a fundamental problem in machine learning with wide applications. A popular formulation of the problem is an …
Theoretical properties of the global optimizer of two layer neural network
Digvijay Boob, Guanghui Lan
In this paper, we study the problem of optimizing a two-layer artificial neural network that best fits a training dataset. We look at this problem in the setting where the number o…