On pure stationary almost Markov Nash equilibria in nonzero-sum ARAT stochastic games.

Anna Jaskiewicz Andrzej S. Nowak

Published in: Math. Methods Oper. Res. (2015)

Keyphrases

stochastic games
nash equilibria
incomplete information
game theory
non stationary
nash equilibrium
game theoretic
multi agent reinforcement learning
markov chain
objective function
learning algorithm
multi agent
cooperative
worst case
learning automata