Experiments with Adaptive Transfer Rate in Reinforcement Learning (original) (raw)

Lecture Notes in Computer Science, 2009

Abstract

Transfer algorithms allow the use of knowledge previously learned on related tasks to speed-up learning of the current task. Recently, many complex reinforcement learning problems have been successfully solved by efficient transfer learners. However, most of these algorithms suffer from a severe flaw: they are implicitly tuned to transfer knowledge between tasks having a given degree of similarity. In other

Yann Chevaleyre hasn't uploaded this paper.

Let Yann know you want this paper to be uploaded.

Ask for this paper to be uploaded.