Enhancing Autonomy with Value-Based Goal Adoption

Luis Antunes, João Faria, and Helder Coelho

Agents must decide what to do and by what order. Autonomy is a key notion in a multi-agent system, since it is the main justification for the unpredictability and complexity of the environment. Autonomy has a role in deciding which are the new goals of the agent, and it has another in choosing which of the agent’s goals are going to be addressed next. Our (BVG) agent architecture relies the use of values (multiple dimensions against which to evaluate a situation) to perform choice among a set of candidate goals. In this paper we propose that values can also be used to guide the adoption of new goals from other agents. In this setting, we introduce rules for adoption and evaluate their impact by conducting experiments to trace the adoption of goals through a simulated society of simple agents.

This page is copyrighted by AAAI. All rights reserved. Your use of this site constitutes acceptance of all of AAAI's terms and conditions and privacy policy.