Distributed Reinforcement Learning in M u lti-a gent Decision Systems
J. Ignacio Giráldez, Daniel Borrajo · 1998
Decision problems can be usually solved using systems that implement different paradigms. These systems may be integrated into a single distributed system, with the expectation of obtaining a group performance more satisfactory than individual performances. Such a dis- tributed system is what we call a Multi Agent Decision System (MADES), a special kind of Multi Agent System, that integrates several heterogeneous autonomous decision systems (agents). A MADES must produce a single solution proposal for the problem instance it faces, de- spite the fact that its decision making is distributed, and every agent produces solution proposals according to its local view and to its id- iosyncrasy. We present a distributed reinforcement algorithm for learning how to combine the decisions the agents make in a distributed way, into a single group decision (solution proposal).