Nonzero-sum stochastic games
GPTKB entity
Statements (23)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
gptkb:mathematical_concept
|
| gptkbp:application |
gptkb:reinforcement_learning
economics multi-agent systems |
| gptkbp:defines |
Games where the sum of payoffs to all players is not constant and depends on the actions taken and the state transitions.
|
| gptkbp:field |
game theory
stochastic processes |
| gptkbp:generalizes |
gptkb:zero-sum_stochastic_games
repeated games Markov decision processes |
| gptkbp:hasProperty |
state transitions
multiple players strategic interaction payoff functions for each player |
| https://www.w3.org/2000/01/rdf-schema#label |
Nonzero-sum stochastic games
|
| gptkbp:introducedIn |
1953
|
| gptkbp:inventedBy |
gptkb:Lloyd_Shapley
|
| gptkbp:relatedTo |
gptkb:Nash_equilibrium
gptkb:nonzero-sum_games stochastic games Markov decision processes |
| gptkbp:bfsParent |
gptkb:Stochastic_Games
|
| gptkbp:bfsLayer |
6
|