eCite Digital Repository

Incorporating expert advice into reinforcement learning using constructive neural networks


Ollington, RB and Vamplew, PH and Swanson, J, Incorporating expert advice into reinforcement learning using constructive neural networks, Constructive Neural Networks, Springer, Leonardo Franco, David A Elizondo and Jose M Jerez (ed), Berlin, Heidelberg, pp. 207-224. ISBN 978-3-642-04511-0 (2009) [Research Book Chapter]

Restricted - Request a copy

Copyright Statement

The original publication is available at

Official URL:

DOI: doi:10.1007/978-3-642-04512-7_11


This paper presents and investigates a novel approach to using expert advice to speed up the learning performance of an agent operating within a rein- forcement learning framework. This is accomplished through the use of a constructive neural network based on radial basis functions. It is demonstrated that incorporating advice from a human teacher can substantially improve the perform- ance of a reinforcement learning agent, and that the constructive algorithm pro- posed is particularly effective at aiding the early performance of the agent, whilst reducing the amount of feedback required from the teacher. The use of construc- tive networks within a reinforcement learning context is a relatively new area of research in itself, and so this paper also provides a review of the previous work in this area, as a guide for future researchers.

Item Details

Item Type:Research Book Chapter
Research Division:Information and Computing Sciences
Research Group:Artificial intelligence
Research Field:Intelligent robotics
Objective Division:Expanding Knowledge
Objective Group:Expanding knowledge
Objective Field:Expanding knowledge in the information and computing sciences
UTAS Author:Ollington, RB (Dr Robert Ollington)
UTAS Author:Swanson, J (Mr John Swanson)
ID Code:60900
Year Published:2009
Deposited By:Information and Communication Technology
Deposited On:2010-02-22
Last Modified:2014-12-09
Downloads:1 View Download Statistics

Repository Staff Only: item control page