Equilibrium in a stochastic $n$-person game

By A. Fink. 1964

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Amy Greenwald
2. Michael P. Wellman
3. Junling Hu
4. Keith B. Hall
5. F. Thuijsman
6. Takuo Sugaya
7. Satoru Takahashi
8. Johannes Hörner

Citations in the corpus

• Nash Q-Learning for General-Sum Stochastic Games (2003, background): “The framework of stochastic games (Filar and Vrieze, 1997, Thusijsman, 1992) models multiagent systems with discrete time 1 and noncooperative nature.”
• Correlated Q-Learning (2003, background): “Forges (1990) establishes that this property holds of correlated equilibria in two-player, zero-sum one-shot games. • It is well known that Nash equilibria in two-player, zero-sum games are “exchangeable” in the following sense (see, for example, Osborne and Rubinstein (1994)): If Γ is a two-player,”
• Learning the IPA market with individual and social rewards (2007, unknown): “So, for us, a NE is a joint demand function, π i =1 ,...,n , with An important result shown by Fink [11] guarantees that every n-player general-sum discounted stochastic game possesses at least one NE point in stationary strategies .”
• Repeated Games with Absorbing States (2003, background): “It is well known from Fink [2] that stationary λ-discounted equilibria exist in any (n-person) stochastic game.”
• Nash Q-Learning for General-Sum Stochastic Games (2003, background): “The framework of stochastic games (Filar and Vrieze, 1997, Thusijsman, 1992) models multiagent systems with discrete time 1 and noncooperative nature.”
• Recursive Methods in Discounted Stochastic Games: An Algorithm for δ→ 1 and a Folk Theorem (2010, background): “Let k ≥ 1, and hk ∈ Hk. As in FL, using ( 6 ), since �sk is a Nash equilibrium of the one-shot game 1(sk,�; ¯ �) with payoff v, it is also a Nash equilibrium of the game with payoff function”