Factorized Q-Learning for Large-Scale Multi-Agent Systems.
Yong ChenMing ZhouYing WenYaodong YangYufeng SuWeinan ZhangDell ZhangJun WangHan LiuPublished in: CoRR (2018)
Keyphrases
- reinforcement learning
- cooperative
- function approximation
- state space
- multi agent
- model free
- learning rate
- learning algorithm
- stochastic approximation
- reinforcement learning algorithms
- action selection
- optimal policy
- matrix factorization
- multi agent reinforcement learning
- potential field
- real world
- relational reinforcement learning
- learning process
- td learning
- bucket brigade
- credit assignment
- single agent
- evolutionary algorithm
- artificial neural networks
- machine learning