The Gauss-Seidel numerical procedure for Markov stochastic games.

Harold J. Kushner

Published in: IEEE Trans. Autom. Control. (2004)

Keyphrases

stochastic games
gauss seidel
nash equilibria
markov decision processes
multiagent reinforcement learning
markov chain
nash equilibrium
neural network
learning automata
multi agent
gauss seidel method
convergence speed
machine learning
robust optimization
infinite horizon
markov model
fixed point
multiagent systems