Adaptive policy for two finite Markov chains zero-sum stochastic game with unknown transition matrices and average payoffs

Automatica

Volumn 37, Issue 7, 2001, Pages 1007-1018

  Najim, K ^a   Poznyak, A S ^b   Gomez, E ^c  

^a UNIVERSITÉ DE TOULOUSE   (France)

^b DEPARTAMENTO DE FÍSICA   (Mexico)

^c UNIVERSIDAD LA SALLE   (Mexico)

Author keywords

Adaptive control; Controlled Markov chains; Stochastic game

Indexed keywords

ADAPTIVE ALGORITHMS; GAME THEORY; LAGRANGE MULTIPLIERS; MARKOV PROCESSES;

CONTROLLED MARKOV CHAINS; STOCHASTIC GAME;

ADAPTIVE CONTROL SYSTEMS;

EID: 0035400337     PISSN: 00051098     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0005-1098(01)00050-4     Document Type: Article

References (25)

1. Adaptive control of constrained Markov chains: Criteria and policies
2. Bilinear Markov processes of search of moving objects
3. Search methods for moving evaders
4. Markov games with incomplete information
5. Stochastic games
6. Stochastic zero-sum game of two automata
7. Adaptive control of constrained finite Markov chains
8. Algorithms for stochastic games - A survey
9. Noncooperative stochastic games
10. A survey on optimality and equilibria in stochastic games
11. Stationary ε-optimal strategies in stochastic games
12. Stochastic games and optimal stationary strategies