ARES 2: a tool for evaluating cooperative and competitive multi-agent systems

  • Authors:

  • Jörg Denzinger;Jordan Kidney

  • Affiliations:

  • Dep of Computer Science, University of Calgary;Dep of Computer Science, University of Calgary

  • Venue:
  • AI'05 Proceedings of the 18th Canadian Society conference on Advances in Artificial Intelligence
  • Year:
  • 2005

Quantified Score

Hi-index 0.00

Visualization

Abstract

The Agent Rescue Emergency Simulator (ARES) system provides a simplified rescue scenario similar to Robocup Rescue for use in the educational or research fields when evaluating multi-agent systems The environment within ARES abstracts ideas down to key features while still allowing for a wide range of scenarios requiring different skills to be presented to the agents This is achieved by combining different features together and changing the configuration of the environmental rules incorporated in ARES With the simplified environment ARES can be used for quick evaluations of concepts based upon the results from a range of different configurations of the system The results from these tests can be used as a basis for further experiments when transitioning the work from a theoretical level to more real world scenarios, where the requirement for a more complex system is needed Our newest version of ARES, ARES 2, allows for scenarios that range from cooperation between all agents to strong competitiveness of agents or even agent teams.