University of Sussex
Browse

File(s) not publicly available

Evolving integrated controllers for autonomous learning robots using dynamic neural networks.

presentation
posted on 2023-06-08, 00:23 authored by Elio Tuci, Inman HarveyInman Harvey, Matt Quinn
In 1994, Yamauchi and Beer (1994) attempted to evolve a dynamic neural network as a control system for a simulated agent capable of performaning learned behaviour. They tried to evolve an integrated network, i.e. not modularized; this attempt failed. They ended up having to use independent evolution of separate controller modules, arbitrarily partitioned by the researcher. Moreover, they "provided" the agents with hard-wired reinforcement signals. The model we describe in this paper demonstrates that it is possible to evolve an integrated dynamic neural network that successfully controls the behaviour of a khepera robot engaged in a simple learning task. We show that dynamic neural networks, based on leaky-integrator neuron, shaped by evolution, appear to be able to integrate reactive and learned behaviour with an integrated control system which also benefits from its own reinforcement signal.

History

Publication status

  • Published

Publisher

MIT Press

Pages

10.0

Presentation Type

  • paper

Event name

Proceedings of The Seventh International Conference on the Simulation of Adaptive Behavior (SAB'02), 4-9 August 2002, Edinburgh, UK.

Event location

Edinburgh

Event type

conference

ISBN

0-262-58217-1

Department affiliated with

  • Informatics Publications

Full text available

  • No

Peer reviewed?

  • Yes

Legacy Posted Date

2012-02-06

Usage metrics

    University of Sussex (Publications)

    Categories

    No categories selected

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC