Perfect-Information Stochastic Games with Generalized Mean-Payoff Objectives.

Krishnendu Chatterjee Laurent Doyen

Published in: CoRR (2016)

Keyphrases

subgame perfect equilibrium
stochastic games
perfect information
imperfect information
repeated games

nash equilibrium
game theory
nash equilibria
game theoretic
markov decision processes

multi agent
learning automata
average reward
game tree
robust optimization

reinforcement learning algorithms
optimal control
linear programming
cooperative
learning algorithm