VAAC: V-value Attention Actor-Critic for Cooperative Multi-agent Reinforcement Learning.
Haonan LiuLiansheng ZhuangYihong HuangCheng ZhaoPublished in: ICONIP (1) (2022)
Keyphrases
- multi agent reinforcement learning
- actor critic
- reinforcement learning
- cooperative
- multi agent
- multi agent systems
- temporal difference
- reinforcement learning algorithms
- learning agents
- multi agent learning
- function approximation
- neuro fuzzy
- learning algorithm
- policy gradient
- optimal control
- learning automata
- policy iteration
- gradient method
- state space
- markov decision processes
- learning agent
- average reward
- stochastic games
- dynamic environments
- machine learning