Attentional Factorized Q-Learning for Many-Agent Learning.
Xiaoqiang WangLiangjun KeQiang FuPublished in: IEEE Access (2022)
Keyphrases
- learning algorithm
- reinforcement learning
- multi agent
- learning systems
- learning agent
- action selection
- learning process
- online learning
- learning capabilities
- temporal difference learning
- prior knowledge
- dynamic environments
- intelligent agents
- reinforcement learning methods
- learning agents
- state action
- decision theoretic
- function approximation
- learning problems
- learning tasks
- knowledge acquisition
- cooperative
- decision making