Learning parametrised RoboCup rescue agent behaviour using an evolutionary algorithm

  • Authors:

  • Michael Kruse;Michael Baumann;Tobias Knieper;Christoph Seipel;Lial Khaluf;Nico Lehmann;Alex Lermontow;Christian Messinger;Simon Richter;Thomas Schmidt;Daniel Swars

  • Affiliations:

  • Students of Computer Science, University of Paderborn;Students of Computer Science, University of Paderborn;Students of Computer Science, University of Paderborn;Students of Computer Science, University of Paderborn;Students of Computer Science, University of Paderborn;Students of Computer Science, University of Paderborn;Students of Computer Science, University of Paderborn;Students of Computer Science, University of Paderborn;Students of Computer Science, University of Paderborn;Students of Computer Science, University of Paderborn;Students of Computer Science, University of Paderborn

  • Venue:
  • KI'09 Proceedings of the 32nd annual German conference on Advances in artificial intelligence
  • Year:
  • 2009

Quantified Score

Hi-index 0.00

Visualization

Abstract

Although various methods have already been utilised in the RoboCup Rescue simulation project, we investigated a new approach and implemented self-organising agents without any central instance. Coordinated behaviour is achieved by using a task allocation system. The task allocation system supports an adjustable evaluation function, which gives the agents options on their behaviour. Weights for each evaluation function were evolved using an evolutionary algorithm. We additionally investigated different settings for the learning algorithm. We gained extraordinary high scores on deterministic simulation runs with reasonable acting agents.