Nash equilibria in a class of Markov stopping games with total reward criterion.
Rolando Cavazos-CadenaMario Cantú-SifuentesImelda Cerda-DelgadoPublished in: Math. Methods Oper. Res. (2021)
Keyphrases
- nash equilibria
- stochastic games
- congestion games
- game theory
- incomplete information
- nash equilibrium
- game theoretic
- fictitious play
- normal form games
- pure strategy
- solution concepts
- optimality criterion
- mixed strategy
- markov chain
- total reward
- machine learning
- reinforcement learning algorithms
- optimal policy
- probability distribution
- cooperative
- reinforcement learning