research
∙
11/20/2019
A Tale of Two-Timescale Reinforcement Learning with the Tightest Finite-Time Bound
Policy evaluation in reinforcement learning is often conducted using two...
share
research
∙
06/03/2019
Optimal Learning of Mallows Block Model
The Mallows model, introduced in the seminal paper of Mallows 1957, is o...
research
∙
05/29/2019
Learning to Crawl
Web crawling is the problem of keeping a cache of webpages fresh, i.e., ...
research
∙
02/06/2019
Bandit Multiclass Linear Classification: Efficient Algorithms for the Separable Case
We study the problem of efficient online multiclass linear classificatio...
research
∙
01/16/2019
The information-theoretic value of unlabeled data in semi-supervised learning
We quantify the separation between the numbers of labeled examples requi...
research
∙
04/04/2017
Finite Sample Analyses for TD(0) with Function Approximation
TD(0) is one of the most commonly used algorithms in reinforcement learn...
research
∙
04/26/2016