John S. Baras


A Distributed Learning Algorithm with Bit-valued Communications for Multi-agent Welfare Optimization

A. Menon, John S. Baras

Proceedings of the 52nd IEEE Conference on Decision and Control, pp. 2406-2411, Firenze, Italy, December 10-13, 2013.

Full Paper (.pdf)


A multi-agent system comprising N agents, each picking actions from a finite set and receiving a payoff that depends on the action of the whole, is considered. The exact form of the payoffs are unknown and only their values can be measured by the respective agents. A decentralized algorithm was proposed by Marden et al. and in the authors’ earlier work that, in this setting, leads to the agents picking welfare optimizing actions under some restrictive assumptions on the payoff structure. This algorithm is modified in this paper to incorporate exchange of certain bit-valued information between the agents over a directed communication graph. The notion of an interaction graph is then introduced to encode known interaction in the system. Restrictions on the payoff structure are eliminated and conditions that guarantee convergence to welfare minimizing actions w.p. 1 are derived under the assumption that the union of the interaction graph and communication graph is strongly connected.


Biography | Site Map | Contact Dr. Baras | Send Feedback | ©2008 ISR