Nash Q-Learning for General-Sum Stochastic Games

By Junling Hu, Michael P. Wellman. 2003

Citations in the corpus

• Multiagent Learning: Basics, Challenges, and Prospects (2012, neutral): “For more details on Nash-Q we refer to Hu and Wellman (2003).”
• Computing Equilibria in Multiplayer Stochastic Games of Imperfect Information (2009, unknown): “For example, Friend-or-Foe Q-learning [11] and Nash-Q [8] converge if the overall stochastic game has a global optimum (a strategy profile that maximizes the payoff for each agent) or a saddle point (Nash equilibrium such that if any agent deviates, all others become better off)—and furthermore, the ”