Re-usable features in a hierarchical concept network for autonomous learning in complex games

Anthony Knittel, Terence Bossomaier

Research output: Book chapter/Published conference paperConference paper

2 Citations (Scopus)

Abstract

The use of re-usable features to define conceptual elements is a recognised trait in many models of semantic memory, and provides advantages in efficiency of presentation, and a manner to preserve links between related concepts. In order to form scalable and generalisable representations, autonomous systems are advantaged by theability to re-use features, and to develop such a network of features autonomously. Existing learning systems that build knowledge structures in a reinforcement based environment tend to use separately defined rules, rather than re-use of shared features. The system described is a form of Learning Classifier System, based on the tivation-Reinforcement Classifier System that reinforces rules according to separate properties of expected reward and accessibility. This provides a useful platform for examining the construction of rules from re-used features. An implementation is described that constructs a network of features, that are used to define rules. This is able to operate successfully on the game of Dots and Boxes, providing stable operation and the ability to activate rules from a body of 4000 autonomously developed features. Examining the network produced shows a scale-free connectivity distribution, which is a property common in human semantic networks.
Original languageEnglish
Title of host publicationEAIS 2011
Subtitle of host publication2011 IEEE Workshop on Evolving and Adaptive Intelligent Systems
Place of PublicationParis
PublisherIEEE, Institute of Electrical and Electronics Engineers
Pages155-162
Number of pages8
ISBN (Electronic)9781424499793
DOIs
Publication statusPublished - 2011
EventThe 2011 IEEE Workshop on Evolving and Adaptive Intelligent Systems (EAIS-2011) - Paris, France, Paris, France
Duration: 11 Apr 201115 Apr 2011
http://ieeexplore.ieee.org/document/5945933/

Workshop

WorkshopThe 2011 IEEE Workshop on Evolving and Adaptive Intelligent Systems (EAIS-2011)
CountryFrance
CityParis
Period11/04/1115/04/11
Internet address

Fingerprint Dive into the research topics of 'Re-usable features in a hierarchical concept network for autonomous learning in complex games'. Together they form a unique fingerprint.

Cite this