Implementation of a tileworld testbed on a distributed blackboard system

Research into multi-agent systems has increased over several years, leading to demand for multi-agent system simulators to investigate the interaction between different agents and their environment. The more complex and intelligent the agents become, the more difficult it is to simulate them. Distributing the simulation across different processors would improve its performance. This paper describes the implementation of a multi-agent test-bed called TileWorld on a distributed blackboard system, DARBS. The slow-down of the simulator on a single processor has been measured as the number of agents increases, and the likely effect of migrating to a multiple-processor system is assessed.