Deep Q-Learning to Preserve Connectivity in Multi-robot Systems.
Wanrong HuangYanzhen WangXiaodong YiPublished in: ICSPS (2017)
Keyphrases
- multi robot systems
- multi agent
- multi robot
- reinforcement learning
- cooperative
- autonomous robots
- function approximation
- multiple robots
- mobile robot
- learning algorithm
- state space
- learning rate
- action selection
- intelligent agents
- multi agent systems
- computer vision
- multi robot task allocation
- optimal policy
- object detection