Linear Complementarity and P-Matrices for Stochastic Games.

Ola Svensson Sergei G. Vorobyov

Published in: Ershov Memorial Conference (2006)

Keyphrases

stochastic games
nash equilibria
incomplete information
multiagent reinforcement learning
markov decision processes
average reward
multi agent
nash equilibrium
imperfect information
optimal policy
learning automata