Learning Parametrised RoboCup Rescue Agent Behaviour Using an Evolutionary Algorithm
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.
KeywordsEvolutionary Algorithm Task Allocation Tournament Selection Coordination Strategy Roulette Wheel Selection
Unable to display preview. Download preview PDF.
- 1.RoboCup Rescue Project, http://www.robocuprescue.org
- 2.PaderRescue: Project-group for Agent-based Disaster Management and Emergent Realtime Rescue for Emergency SCenarios in Uncertain Environments, University of Paderborn, http://wwwcs.uni-paderborn.de/cs/ag-klbue/de/research/PaderRescue/pgrescue.html
- 3.Stef, B.M.P., Maurits, L.F., Visser, A.: The High-Level Communication Model for Multi-agent Coordination in the RoboCupRescue Simulator. In: Polani, D., Browning, B., Bonarini, A., Yoshida, K. (eds.) RoboCup 2003. LNCS (LNAI), vol. 3020, pp. 503–509. Springer, Heidelberg (2004)Google Scholar
- 4.Ohta, M.: An Implementation of Rescue Agents with Genetic Algorithm. In: 2nd International Workshop on Synthetic Simulation and Robotics to Mitigate Earthquake Disaster, Lisbon (2004), http://www.rescuesystem.org/robocuprescue/SRMED2004/MOhta.pdf