Convergence of Multi-Agent Learning with a Finite Step Size in General-Sum Games.
Xinliang SongTonghan WangChongjie ZhangPublished in: CoRR (2019)
Keyphrases
- step size
- multi agent learning
- convergence rate
- convergence speed
- faster convergence
- variable step size
- learning agents
- game theory
- cost function
- multi agent
- learning rate
- artificial intelligence
- gradient method
- temporal difference
- differential evolution
- complex domains
- nash equilibrium
- particle swarm optimization
- pso algorithm
- cooperative
- machine learning