Loughborough University
Browse
soltoggioJonesGECCO2009.pdf (611.72 kB)

Novelty of behaviour as a basis for the neuro-evolution of operant reward learning

Download (611.72 kB)
conference contribution
posted on 2015-03-18, 15:32 authored by Andrea SoltoggioAndrea Soltoggio, Ben H. Jones
An agent that deviates from a usual or previous course of action can be said to display novel or varying behaviour. Novelty of behaviour can be seen as the result of real or apparent randomness in decision making, which prevents an agent from repeating exactly past choices. In this paper, novelty of behaviour is considered as an evolutionary precursor of the exploring skill in reward learning, and conservative behaviour as the precursor of exploitation. Novelty of behaviour in neural control is hypothesised to be an important factor in the neuro-evolution of operant reward learning. Agents capable of varying behaviour, as opposed to conservative, when exposed to reward stimuli appear to acquire on a faster evolutionary scale the meaning and use of such reward information. The hypothesis is validated by comparing the performance during evolution in two environments that either favour or are neutral to novelty. Following these findings, we suggest that neuro-evolution of operant reward learning is fostered by environments where behavioural novelty is intrinsically beneficial, i.e. where varying or exploring behaviour is associated with low risk.

History

School

  • Science

Department

  • Computer Science

Published in

Proceedings of the 11th Annual Genetic and Evolutionary Computation Conference, GECCO-2009

Pages

169 - 176

Citation

SOLTOGGIO, A. and JONES., B.H., 2009. Novelty of behaviour as a basis for the neuro-evolution of operant reward learning. IN: Proceedings of the 11th Annual Genetic and Evolutionary Computation Conference, GECCO-2009, pp. 169 - 176.

Publisher

© ACM

Version

  • AM (Accepted Manuscript)

Publisher statement

This work is made available according to the conditions of the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0) licence. Full details of this licence are available at: https://creativecommons.org/licenses/by-nc-nd/4.0/

Publication date

2009

Notes

This is a conference paper.

ISBN

9781605583259

Language

  • en

Usage metrics

    Loughborough Publications

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC