Safe end-to-end imitation learning for model predictive control.
Keuntaek LeeKamil SaigolEvangelos A. TheodorouPublished in: CoRR (2018)
Keyphrases
- end to end
- imitation learning
- model predictive control
- control system
- predictive control
- reinforcement learning
- robotic systems
- maximum margin
- humanoid robot
- congestion control
- reinforcement learning methods
- closed loop
- neural network
- semi supervised learning
- fuzzy logic
- multi class
- data points
- mobile robot
- relational databases
- mpc algorithm