Distributed control by Lagrangian steepest descent

Often adaptive, distributed control can be viewed as an iterated game between independent players. The coupling between the players' mixed strategies, arising as the system evolves, is determined by the system designer. Information theory tells us that the most likely joint strategy of the players, given a value of the expectation of the overall control objective function, is the minimizer of a Lagrangian function of the joint strategy. So the goal of the system designer is to speed evolution of the joint strategy to that Lagrangian minimizing point, lower the expected value of the control objective function, and repeat. Here, we discuss how to do this using local descent procedures, and thereby achieve efficient, adaptive, distributed control.

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

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

[3]  David H. Wolpert,et al.  Product distribution theory for control of multi-agent systems , 2004, Proceedings of the Third International Joint Conference on Autonomous Agents and Multiagent Systems, 2004. AAMAS 2004..

[4]  O. Catoni.  Solving Scheduling Problems by Simulated Annealing , 1998 .

[5]  T. Başar,et al.  Dynamic Noncooperative Game Theory , 1982 .

[6]  S. Hart,et al.  Handbook of Game Theory with Economic Applications , 1992 .

[7]  R. Weiner.  Lecture Notes in Economics and Mathematical Systems , 1985 .

[8]  D. Wolpert,et al.  Product Distribution Theory and Semi-Coordinate Transformations , 2004 .

[9]  Jason L. Speyer,et al.  Decentralized controllers for unmanned aerial vehicle formation flight , 1996 .

[10]  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..

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

[12]  David G. Stork,et al.  Pattern Classification (2nd ed.) , 1999 .

[13]  Richard D. Braatz,et al.  Robust performance of cross-directional basis-weight control in paper machines , 1993, Autom..

[14]  D. Wolpert,et al.  Self-dissimilarity as a High Dimensional Complexity Measure , 2005 .

[15]  M. Tribus,et al.  Probability theory: the logic of science , 2003 .

[16]  Ariel Rubinstein,et al.  A Course in Game Theory , 1995 .

[17]  R. Vidal.  Applied simulated annealing , 1993 .

[18]  Thomas M. Cover,et al.  Elements of Information Theory , 2005 .

[19]  David H. Wolpert,et al.  Discrete, Continuous, and Constrained Optimization Using Collectives , 2004 .

[20]  David H. Wolpert,et al.  Information Theory - The Bridge Connecting Bounded Rational Game Theory and Statistical Physics , 2004, ArXiv.

[21]  David G. Stork,et al.  Pattern Classification , 1973 .

[22]  Reinhard Lüling,et al.  Problem Independent Distributed Simulated Annealing and its Applications , 1993 .

[23]  C. D. Gelatt,et al.  Optimization by Simulated Annealing , 1983, Science.

[24]  M. Mesbahi,et al.  Graphs, matrix inequalities, and switching for the formation flying control of multiple spacecraft , 1999, Proceedings of the 1999 American Control Conference (Cat. No. 99CH36251).

[25]  Shigeo Abe DrEng.  Pattern Classification , 2001, Springer London.

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