Commitment and Effectiveness of Situated Agents

Recent research in real-time Artificial Intelligence has focussed upon the design of situated agents and, in particular, how to achieve effective and robust behaviour with limited computational resources. A range of architectures and design principles has been proposed to solve this problem. This has led to the development of simulated worlds that can serve as testbeds in which the effectiveness of different agents can be evaluated. We report here an experimental program that aimed to investigate how commitment to goals contributes to effective behaviour and to compare the properties of different strategies for reacting to change. Our results demonstrate the feasibility of developing systems for empirical measurement of agent performance that are stable, sensitive, and capable of revealing the effect of "high-level" agent characteristics such as commitment.