F2A2: Flexible Fully-decentralized Approximate Actor-critic for Cooperative Multi-agent Reinforcement Learning.
Wenhao LiBo JinXiangfeng WangJunchi YanHongyuan ZhaPublished in: J. Mach. Learn. Res. (2023)
Keyphrases
- multi agent reinforcement learning
- cooperative
- actor critic
- reinforcement learning
- multi agent
- multi agent systems
- optimal control
- distributed control
- learning agents
- multi agent learning
- reinforcement learning algorithms
- policy gradient
- function approximation
- temporal difference
- gradient method
- game theory
- dynamical systems
- learning agent
- stochastic games
- neural network
- policy iteration
- neuro fuzzy
- autonomous agents