The Value Function with Regret Minimization Algorithm for Solving the Nash Equilibrium of Multi-Agent Stochastic Game.
Luping LiuWensheng JiaPublished in: Int. J. Comput. Intell. Syst. (2021)
Keyphrases
- regret minimization
- nash equilibrium
- game theoretic
- game theory
- multi agent
- fictitious play
- worst case
- learning algorithm
- dynamic programming
- reinforcement learning
- multi agent learning
- solution concepts
- single agent
- computational complexity
- cooperative
- state space
- variational inequalities
- np hard
- nash equilibria
- repeated games
- search space
- lower bound
- mixed strategy
- profit maximizing