Distributed learning of the global maximum in a two-player stochastic game with identical payoffs Academic Article uri icon

abstract

  • Little is known about the distributed learning of the global maximum in a stochastic framework when there is no communication between the decision-makers. The case of two decision-makers is considered, and prior knowledge is assumed about the expected rewards. The prior knowledge captures the asymmetries that may be present in the rewards. It is shown that each decision-maker completely unaware of the other converges to the global optimum with arbitrary accuracy over time.

published proceedings

  • IEEE Transactions on Systems Man and Cybernetics

altmetric score

  • 3

author list (cited authors)

  • Kumar, P., & Young, G.

citation count

  • 3

publication date

  • November 1985