Factorized Q-learning for large-scale multi-agent systems.
Ming ZhouYong ChenYing WenYaodong YangYufeng SuWeinan ZhangDell ZhangJun WangPublished in: DAI (2019)
Keyphrases
- reinforcement learning
- state space
- function approximation
- cooperative
- learning algorithm
- multi agent
- action selection
- learning rate
- model free
- stochastic approximation
- optimal policy
- matrix factorization
- dynamic programming
- reinforcement learning algorithms
- bucket brigade
- potential field
- temporal difference learning
- credit assignment
- td learning
- multi agent reinforcement learning
- learning agent
- machine learning
- traffic signal
- multiagent learning
- temporal difference
- hierarchical reinforcement learning
- real world
- database