ePapers Repository

Neuroevolution of Agents Capable of Reactive and Deliberative Behaviours in Novel and Dynamic Environments

Robinson, Edward and Ellis, Timothy and Channon, Alastair (2007) Neuroevolution of Agents Capable of Reactive and Deliberative Behaviours in Novel and Dynamic Environments. Advances In Artificial Life, 4648. pp. 345-354. ISSN 0302-9743

[img]
Preview
PDF (LaTeX and dvi2pdf)
ecal2007.pdf
339Kb

URL of Published Version: http://dx.doi.org/10.1007/978-3-540-74913-4

Identification Number/DOI: 10.1007/978-3-540-74913-4

Abstract

Both reactive and deliberative qualities are essential for a good action selection mechanism. We present a model that embodies a hybrid of two very different neural network architectures inside an animat: one that controls their high level deliberative behaviours, such as the selection of sub-goals, and one that provides reactive and navigational capabilities. Animats using this model are evolved in novel and dynamic environments, on complex tasks requiring deliberative behaviours: tasks that cannot be solved by reactive mechanisms alone and which would traditionally have their solutions formulated in terms of search-based planning. Significantly, no a priori information is given to the animats, making explicit forward search through state transitions impossible. The complexity of the problem means that animats must first learn to solve sub-goals without receiving any reward. Animats are shown increasingly complex versions of the task, with the results demonstrating, for the first time, incremental neuro-evolutionary learning on such tasks.

Type of Work:Article
School/Faculty:Schools (1998 to 2008) > School of Computer Science
Department:Natural Computation
Projects:Msc Natural Computation Mini-Project
Keywords:Artificial Life, Neural Networks, Incremental Evolution, Re- active and Deliberative Systems, Novel and Dynamic Environments
Subjects:H Social Sciences > H Social Sciences (General)
Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Related URLs:
URLURL Type
http://www.cs.bham.ac.uk/~eyrAuthor
Funders:Partially funded by EPSRC Studentship
Copyright Status:© Springer-Verlag (http://www.springer.de/comp/lncs/index.html)
Copyright Holders:Springer-Verlag
ID Code:32
Local Holdings:

Export Reference As : ASCII + BibTeX + Dublin Core + EndNote + HTML + METS + MODS + OpenURL Object + Reference Manager + Refer + RefWorks
Share this item :
QR Code for this page

Repository Staff Only: item control page