Agent Architectures for Flexible
Milind Tambe · 1997
Teamwork in complex, dynamic, multi-agent domains man-dates highly flexible coordination and communication. Sim-ply fitting individual agents with precomputed coordination plans will not do, for their inflexibility can cause severe failures in teamwork, and their domain-specificity hinders reusability. Our central hypothesis is that the key to such flexibility and reusability is agent architectures with inte-grated teamwork capabilities. This fundamental shift in agent architectures i illustrated via an implemented can-didate: STEAM. While STEAM is founded on the j&t intentions theory, practical operationalization has required it to integrate several key novel concepts: (i) team synchro-nization to establish joint intentions; (ii) constructs for moni-toring joint intentions and repair; and (iii) decision-theoretic communication selectivity (to pragmatically extend the joint intentions theory). Applications in three different complex domains, with empirical results, are presented. 1