ACE: Cooperative Multi-Agent Q-learning with Bidirectional Action-Dependency.
Chuming LiJie LiuYinmin ZhangYuhong WeiYazhe NiuYaodong YangYu LiuWanli OuyangPublished in: AAAI (2023)
Keyphrases
- cooperative multi agent
- action selection
- reinforcement learning
- state action
- multi agent
- cooperative
- function approximation
- state space
- logic programming
- learning algorithm
- model free
- reinforcement learning algorithms
- decision making
- search algorithm
- artificial intelligence
- human actions
- action space
- bucket brigade
- agent receives
- stochastic shortest path