Nash Equilibrium Solution Based on Safety-Guarding Reinforcement Learning in Nonzero-Sum Game.
Junkai TanShuangsi XueHui CaoHuan LiPublished in: ICARM (2023)
Keyphrases
- nash equilibrium
- game theory
- reinforcement learning
- game theoretic
- variational inequalities
- pure strategy
- nash equilibria
- pareto optimal
- solution concepts
- stackelberg game
- fictitious play
- stochastic games
- equilibrium strategies
- regret minimization
- mixed strategy
- imperfect information
- repeated games
- subgame perfect
- mechanism design
- machine learning
- function approximation
- worst case
- infinite horizon
- markov decision processes
- evolutionary algorithm
- pure nash equilibria
- decision making