File(s) under permanent embargo
Incorporating expert advice into reinforcement learning using constructive neural networks
chapter
posted on 2023-05-22, 12:19 authored by Robert OllingtonRobert Ollington, Vamplew, PH, Swanson, JThis 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.
History
Publication title
Constructive Neural NetworksEdition
1stEditors
Leonardo Franco, David A Elizondo and Jose M JerezPagination
207-224ISBN
978-3-642-04511-0Department/School
School of Information and Communication TechnologyPublisher
SpringerPlace of publication
Berlin, HeidelbergExtent
15Rights statement
The original publication is available at http://www.springerlink.comRepository Status
- Restricted