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.