We present a framework for knowledge transfer from one reinforcement learning task to a related task through advicetaking mechanisms. We discuss the importance of transfer in comp...
Lisa Torrey, Trevor Walker, Jude W. Shavlik, Richa...
We describe a reinforcement learning system that transfers skills from a previously learned source task to a related target task. The system uses inductive logic programming to ana...
Lisa Torrey, Jude W. Shavlik, Trevor Walker, Richa...
In this paper, we design a local classification algorithm using implicit link analysis, considering the situation that the labeled and unlabeled data are drawn from two different ...
In this paper, we introduce a method that automatically builds text classifiers in a new language by training on already labeled data in another language. Our method transfers the...
Many parallel scientific applications need high-performance I/O. Unfortunately, end-to-end parallel-I/O performance has not been able to keep up with substantial improvements in p...