Improving control through subsumption in the evotanks domain

  • Authors:
  • Tommy Thompson;Fraser Milne;Alastair Andrew;John Levine

  • Affiliations:
  • University of Strathclyde, Glasgow, UK; ;University of Strathclyde, Glasgow, UK;University of Strathclyde, Glasgow, UK

  • Venue:
  • CIG'09 Proceedings of the 5th international conference on Computational Intelligence and Games
  • Year:
  • 2009

Quantified Score

Hi-index 0.00

Visualization

Abstract

In this paper we further explore the potential of a decentralised controller architecture that places multi-layer perceptrons within a subsumption hierarchy. Previous research exploring this approach proved successful in generating agents that could solve problems while coping with new reactive stimuli. However there were many unresolved questions that we wished to explore. In this paper we explore the use of our architecture with iterative training, increased controller modularity and conflicting goals. Results provide some interesting insights into the potential this method could have to agent designers.