An architecture for a rational agent must allow for means-end reasoning, for the weighing of competing alternatives, and for interactions between these two forms of reasoning. Such an architecture must also address the problem of resource boundedness. We sketch a solution of the first problem that points the way to a solution of the second. In particular, we present a high-level specification of the practical-reasoning component of an architecture for a resource-bounded rational agent. In this architecture, a major role of the agent's plans is to constrain the amount of further practical reasoning she must perform. Bratman, Israel, and Pollack 3 1 Introduction Rational behavior---the production of actions that further the goals of an agent, based upon her conception of the world---has long interested researchers in artificial intelligence, who are attempting to build machines that behave rationally, as well as philosophers of mind and action, decision theorists, and others who are a...

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. 1

During the last few years, researchers in Artificial Intelligence have become increasingly concerned with the problem of designing architectures for intelligent systems that are required to operate in complex dynamic environments. The potential applications are both diverse and economically important---for example, the management of air traffic and other transport services; the control of telecommunications, power, and computer networks; transaction management in banks and insurance companies; the monitoring and control of industrial processes; on-line fault diagnosis and malfunction handling; the supervision and control of manufacturing operations; the provision and monitoring of medical care; and the control of industrial robots. In this paper, we discuss some of the issues that arise in the design of intelligent systems that must operate effectively given the time and information constraints imposed by their environment. 1 Introduction Humans spend a great deal of time deciding a...