A learning approach to the two person decentralized team problem with incomplete information

作者: S. Lakshmivarahan

DOI: 10.1016/0096-3003(81)90035-7

关键词:

摘要: A learning approach to the two person decentralized team problem with incomplete information and a 2X2 payoff matrix is considered. It shown that if unimodal, there exists proper choice of parameters algorithm will ensure asymptotically an expected as close maximum desired. multimodal gives rise interesting class open problems.

参考文章(16)
Kumpati S. Narendra, Lena S. Valavani, Direct and Indirect Adaptive Control IFAC Proceedings Volumes. ,vol. 11, pp. 1981- 1987 ,(1978) , 10.1016/S1474-6670(17)66174-3
M. Frank Norman, Markovian Learning Processes SIAM Review. ,vol. 16, pp. 143- 162 ,(1974) , 10.1137/1016025
R. Viswanathan, Kumpatl S. Narendra, Games of Stochastic Automata IEEE Transactions on Systems, Man, and Cybernetics. ,vol. SMC-4, pp. 131- 135 ,(1974) , 10.1109/TSMC.1974.5408539
A. P. Sanghvi, M. J. Sobel, Bayesian games as stochastic processes International Journal of Game Theory. ,vol. 5, pp. 1- 22 ,(1976) , 10.1007/BF01770983
Y.-C. Ho, K.-C. Chu, Correction to "Team decision theory and information structures in optimal control problems," Parts I and II IEEE Transactions on Automatic Control. ,vol. 17, pp. 417- 417 ,(1972) , 10.1109/TAC.1972.1100016
Alireza Akbari, James Hess, Harriet Kagiwada, Robert Kalaba, The equivalence of team theory's integral equations and a Cauchy system: sensitivity analysis of a variational problem Applied Mathematics and Computation. ,vol. 6, pp. 21- 36 ,(1980) , 10.1016/0096-3003(80)90013-2
J. Marschak, Elements for a Theory of Teams Management Science. ,vol. 1, pp. 127- 137 ,(1955) , 10.1287/MNSC.1.2.127
M. Frank Norman, A Central Limit theorem for Markov Processes that Move by Small Steps Annals of Probability. ,vol. 2, pp. 1065- 1074 ,(1974) , 10.1214/AOP/1176996498
Vincent P. Crawford, Learning the Optimal Strategy in a Zero-Sum Game Econometrica. ,vol. 42, pp. 885- 891 ,(1974) , 10.2307/1913795