Robust and High-Precision End-to-End Control Policy for Multi-stage Manipulation Task with Behavioral Cloning.
Wei GeWeiwei ShangFangjing SongHongjian SuiShuang CongPublished in: ICCSIP (1) (2018)
Keyphrases
- end to end
- high precision
- multistage
- admission control
- control policy
- high recall
- production system
- average cost
- single stage
- stochastic programming
- stochastic optimization
- long run
- congestion control
- ad hoc networks
- dynamic programming
- lot sizing
- optimal policy
- control policies
- wireless ad hoc networks
- achieve high precision
- internet protocol
- reinforcement learning
- text localization and recognition
- scalable video
- high accuracy
- transport layer
- wireless sensor networks