Product Distribution Theory and Semi-Coordinate Transformations

Product Distribution (PD) theory is a new framework for doing distributed adaptive control of a multiagent system (MAS). We introduce the technique of "coordinate transformations" in PD theory gradient descent. These transformations selectively couple a few agents with each other into "meta-agents". Intuitively, this can be viewed as a generalization of forming binding contracts between those agents. Doing this sacrifices a bit of the distributed nature of the MAS, in that there must now be communication from multiple agents in determining what joint-move is finally implemented However, as we demonstrate in computer experiments, these transformations improve the performance of the MAS.

[1]  L. Goddard.  Information Theory , 1962, Nature.

[2]  Robert B. Ash,et al.  Information Theory , 2020, The SAGE International Encyclopedia of Mass Media and Society.

[3]  Drew Fudenberg,et al.  Game theory (3. pr.) , 1991 .

[4]  Andrew G. Barto,et al.  Improving Elevator Performance Using Reinforcement Learning , 1995, NIPS.

[5]  D. Fudenberg,et al.  The Theory of Learning in Games , 1998 .

[6]  Kagan Tumer,et al.  Collective Intelligence for Control of Distributed Dynamical Systems , 1999, ArXiv.

[7]  Kagan Tumer,et al.  Optimal Payoff Functions for Members of Collectives , 2001, Adv. Complex Syst..

[8]  Kagan Tumer,et al.  Collective Intelligence, Data Routing and Braess' Paradox , 2002, J. Artif. Intell. Res..

[9]  David H. Wolpert,et al.  Adaptive, distributed control of constrained multi-agent systems , 2004, Proceedings of the Third International Joint Conference on Autonomous Agents and Multiagent Systems, 2004. AAMAS 2004..

[10]  Ilan Kroo,et al.  Fleet Assignment Using Collective Intelligence , 2004 .

[11]  Stefan R. Bieniawski,et al.  Adaptive Multi-Agent Systems for Constrained Optimization , 2004 .

[12]  David J. C. MacKay,et al.  Information Theory, Inference, and Learning Algorithms , 2004, IEEE Transactions on Information Theory.