Comparison of end-to-end and hybrid deep reinforcement learning strategies for controlling cable-driven parallel robots.
Hao XiongTianqi MaLin ZhangXiumin DiaoPublished in: Neurocomputing (2020)
Keyphrases
- end to end
- learning strategies
- active learning
- online learning
- reinforcement learning
- ad hoc networks
- admission control
- computer based instruction
- wireless ad hoc networks
- mental models
- high bandwidth
- scalable video
- congestion control
- multipath
- cooperative
- internet protocol
- data sets
- content delivery
- rate allocation
- blended learning
- motion estimation
- social cognitive theory