Learning Situation-Specific Coordination in Generalized Partial Global Planning

Adaptation, Coevolution, and Learning in Multiagent Systems

Volume

Papers from the 1996 AAAI Spring Symposium

Contents

Achieving effective cooperation in a multi-agent system is a difficult problem for a number of reasons llke local views of problem-solvlng task and uncertainty about the outcomes of interacting non-local tasks. Algorithms llke Generalized Partial Global Planning (GPGP) have responded to these problems by cresting sophiticated coordination mechanisms trigerred in response to the characteristics of particular task environments. In this paper, we present a learning algorithm that endows agents with the capability to choose a suitable subset of the coordination mechanisms based on the present problem solving situation.