Multiagent reinforcement learning: algorithm converging to Nash equilibrium in general-sum discounted stochastic games.

Natalia Akchurina Multiagent reinforcement learning: algorithm converging to Nash equilibrium in general-sum discounted stochastic games. 725-732 2009 AAMAS (2) http://doi.acm.org/10.1145/1558109.1558112 conf/atal/2009-2 db/conf/atal/aamas2009-2.html#Akchurina09