MAPPG: Multi-Agent Phasic Policy Gradient.
Qi ZhangXuetao ZhangYisha LiuXuebo ZhangYan ZhuangPublished in: CDC (2023)
Keyphrases
- policy gradient
- multi agent
- single agent
- reinforcement learning
- actor critic
- partially observable markov decision processes
- parametric optimization
- multi agent systems
- model free reinforcement learning
- function approximation
- optimal control
- multiple agents
- gradient method
- cooperative
- reinforcement learning algorithms
- average reward
- variance reduction
- partially observable
- decision problems
- dynamic environments
- artificial neural networks
- learning algorithm