Robinson, E, Ellis, T and Channon, AD ORCID: https://orcid.org/0000-0001-9224-4931 (2007) Neuroevolution of agents capable of reactive and deliberative behaviours in novel and dynamic environments. Advances in Artificial Life, Proceedings, 4648. 345 - 354.

[img]
Preview
Text
Neuroevolution of agents capable of reactive and deliberative behaviours in novel and dynamic environments (AChannon).pdf

Download (347kB) | Preview

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.

Item Type: Article
Uncontrolled Keywords: artificial life; neural networks; incremental evolution; reactive and deliberative systems; novel and dynamic environments
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions: Faculty of Natural Sciences > School of Computing and Maths
Related URLs:
Depositing User: Symplectic
Date Deposited: 23 Oct 2014 13:20
Last Modified: 16 Jul 2019 12:52
URI: http://eprints.keele.ac.uk/id/eprint/30

Actions (login required)

View Item View Item