A constructive spiking neural network for reinforcement learning in autonomous control

Date

2010

Authors

Lightheart, T.
Grainger, S.
Lu, T.

Editors

Advisors

Journal Title

Journal ISSN

Volume Title

Type:

Conference paper

Citation

Proceedings of the 2010 Australasian Conference on Robotics & Automation, 1-3 December, 2010 Brisbane, Australia / G. Wyeth and B. Upcroft (eds.): 8 p.

Statement of Responsibility

Toby Lightheart, Steven Grainger and Tien-Fu Lu

Conference Name

ACRA 2010

Abstract

This paper presents a method that draws upon reinforcement learning to perform autonomous learning through the automatic construction of a spiking artificial neural network. Constructive neural networks have been applied previously to state and action-value function approximation but have encountered problems of excessive growth of the network, difficulty generalising across a range of problems and a lack of clarity in the operation of resultant networks. The results presented here demonstrate that rapid learning of the control of an inverted pendulum can be achieved with automatic construction of an efficient spiking neural network with internal reward-value associations. This provides a new approach to reinforcement learning and automatic neural network construction for autonomous learning.

School/Discipline

Dissertation Note

Provenance

Description

Access Status

Rights

Copyright status unknown

License

Grant ID

Call number

Persistent link to this record