Advances in distributed optimization using probability collectives

Advances in Complex Systems

Volumn 9, Issue 4, 2006, Pages 383-436

  Wolpert, David H ^a   Strauss, Charlie E M ^b   Rajnarayan, Dev ^c  

^a NASA AMES RESEARCH CENTER   (United States)

^b LOS ALAMOS NATIONAL LABORATORY   (United States)

^c 496 Lomita Mall   (United States)

Author keywords

Distributed control; Distributed optimization; Probability collectives

Indexed keywords

EID: 33847328786     PISSN: 02195259     EISSN: None     Source Type: Journal    
DOI: 10.1142/S0219525906000884     Document Type: Article

References (37)

1. Wolpert, D. H., Product distribution field theory, cond-mat/0307630 (2003).
2. Wolpert, D. H., Information theory - The bridge connecting bounded rational game theory and statistical physics, in Complex Engineering Systems, eds. Braha, D., Minai, A. and Bar-Yam, Y. (Springer, 2004), pp. 262-290.
3. Wolpert, D. H., Tumer, K. and Bandari, E., Improving search by using intelligent coordinates, Phys. Rev. E 69, 017701 (2004).
4. Wolpert, D. H. and Turner, K., Optimal payoff functions for members of collectives, Adv. Complex Syst. 4(2/3), 265-279 (2001).
5. Bieniawski, S., Kroo, I. and Wolpert, D. H., Flight control with distributed effectors, in Proc. 2005 AIAA Guidance, Navigation, and Control Conference, San Francisco, CA (2005), AIAA Paper 2005-6074.
6. Macready, W., Bieniawski, S. and Wolpert, D., Adaptive multi-agent systems for constrained optimization, Technical Report IC-04-123 (2004).
7. Lee, C. F. and Wolpert, D. H., Product distribution theory and semi-coordinate transformations, in Proc. 3rd Int. Conf. on Autonomous Agents and Multiagent Systems, Columbia University (ACM Press, 2004), pp. 522-529.
8. Wolpert, D. H. and Bieniawski, S., Distributed control by Lagrangian steepest descent, in Proc. 2004 IEEE Control and Decision Conf., Nassau, Bahamas (2004), pp. 1562-1567.
9. Wolpert, D. H. and Bieniawsk, S., Adaptive distributed control: beyond single-instant categorical variables, in Proc. MSRAS04, Gdansk Poland, ed. Skowron, A. (Springer Verlag, 2004).
10. Bieniawski, S. and Wolpert, D. H., Adaptive, distributed control of constrained multiagent systems, in Proc. 3rd Int. Conf. on Autonomous Agents and Multiagent Systems, Columbia University (ACM Press, 2004), pp. 1230-1231.
11. Bieniawski, S., Wolpert, D. H. and Kroo, I., Discrete, continuous, and constrained optimization using collectives, in Proc. 10th AIAA/ISSMO Multidisciplinary Analysis and Optimization Conf., Albany, New York (2004).
12. Antoine, N., Bieniawski, S., Kroo, I. and Wolpert, D. H., Fleet assignment using collective intelligence, in Proc. 42nd Aerospace Sciences Meeting (2004), AIAA-2004-0622.
13. Wolpert, D. H. and Lee, C. F., Adaptive Metropolis-Hastings sampling using product distributions, cond-mat/0504163 (2004).
14. Wolpert, D. H., What information theory says about best response, binding contracts, and collective intelligence, in Proc. WEHIA04, Kyoto University, Japan, ed. Namatame, A. (Springer Verlag, 2004).
15. Wolpert, D. H., Tumer, K. and Frank, J., Using collective intelligence to route internet traffic, in Adv. Neural Information Processing Systems -11 (MIT Press, 1999), pp. 952-958.
16. Wolpert, D. H. and Tumer, K., Collective intelligence, data routing and Braess' Paradox, J. Artif. Intell. Res. 16, 359-387 (2002).
17. Wolpert, D. H., Theory of collective intelligence, in Collectives and the Design of Complex Systems, eds. Tumer, K. and Wolpert, D. H. (Springer, New York, 2003).
18. Macready, W. and Wolpert, D. H., Distributed constrained optimization with semicoordinate transformations, submitted to J. Operations Res. (2005).
19. Meginniss, J. R., A new class of symmetric utility rules for gambles, subjective marginal probability functions, and a generalized Bayes' rule, Proc. American Statisticical Association, Business and Economics Statistics Section (1976), pp. 471-476.
20. Fudenberg, D. and Levine, D. K., The Theory of Learning in Games (MIT Press, Cambridge, 1998).
21. Shamma, J. and Arslan, G., Dynamic fictitious play, dynamic gradient play, and distributed convergence to nash equilibria, IEEE Trans. Autom. Control 50(3), 312-327 (2004).
22. Jaynes, E. T., Information theory and statistical mechanics, Phys. Rev. 106, 620 (1957).
23. De Bonet, J., Isbell, C. Jr, and Viola, P., Mimic: Finding optima by estimating probability densities, in Advances in Neural Information Processing Systems - 9 (MIT Press, 1997).
24. Rubinstein, R. and Kroese, D., The Cross-Entropy Method (Springer, 2004).
25. Sabes, P. and Jordan, M., Reinforcement learning by probability matching, in Advances in Neural Information Processing Systems - 8 (MIT Press, 1995).
26. Boyd, S. and Vandenberghe, L., Convex Optimization (Cambridge University Press, 2003).
27. Basar, T. and Olsder, G., Dynamic Noncooperative Game Theory, 2nd edn. (Siam, Philadelphia, PA, 1999).
28. Fudenberg, D. and Tirole, J., Game Theory (MIT Press, Cambridge, MA, 1991).
29. Fudenberg, D. and Kreps, D., Learning mixed equilibria, Game Econ. Behav. 5, 320-367 (1993).
30. Fudenberg, D. and Levine, D. K., Steady state learning and Nash equilibrium, Econometrica, 61(3), 547-573 (1993).
31. Wolpert, D. H. and Macready, W., Self-dissimilarity as a high dimensional complexity measure, in Proc. 5th Int. Conf. on Complex Systems, Boston, MA (2004).
32. Cover, T. and Thomas, J., Elements of Information Theory (Wiley-Interscience, New York, 1991).
33. Duda, R. O., Hart, P. E. and Stork, D. G., Pattern Classification, 2nd edn. (Wiley and Sons, 2000).
34. Mackay, D., Information Theory, Inference, and Learning Algorithms (Cambridge University Press, 2003).
35. Sutton, R. S. and Barto, A. G., Reinforcement Learning: An Introduction (MIT Press Cambridge, MA, 1998).
36. Bieniawski, S. and Wolpert, D. H., Using product distributions for distributed optimization, in Proc. 5th Int. Conf. on Complex Systems, Boston, MA (2004).
37. Wolpert, D. H. and Macready, W. G., No free lunch theorems for optimization, IEEE Trans. Evolut. Comput. 1(1), 67-82 (1997).