A reinforcement learning algorithm acquires demonstration from the training agent by dividing the task space.
Lipeng ZuXiao HeJia YangLianqing LiuWenxue WangPublished in: Neural Networks (2023)
Keyphrases
- multi agent systems
- multi agent
- decision making
- space time
- intelligent agents
- multiagent systems
- online learning
- cooperative
- search algorithm
- higher dimensional
- agent model
- training samples
- software agents
- action selection
- genetic algorithm
- training algorithm
- dynamic environments
- low dimensional
- search space
- training set