Adaptive policy for two finite Markov chains zero-sum stochastic game with unknown transition matrices and average payoffs

Kaddour Najim, Alexander S. Poznyak, E. Gomez. Adaptive policy for two finite Markov chains zero-sum stochastic game with unknown transition matrices and average payoffs. Automatica, 37(7):1007-1018, 2001. [doi]

Authors

Kaddour Najim

This author has not been identified. Look up 'Kaddour Najim' in Google

Alexander S. Poznyak

This author has not been identified. Look up 'Alexander S. Poznyak' in Google

E. Gomez

This author has not been identified. Look up 'E. Gomez' in Google