LQG Online Learning.
Giorgio GneccoAlberto BemporadMarco GoriMarcello SanguinetiPublished in: Neural Comput. (2017)
Keyphrases
- online learning
- optimal control
- motion planning
- linear quadratic
- online course
- dynamic programming
- e learning
- control strategy
- dynamical systems
- degrees of freedom
- mobile robot
- active learning
- reinforcement learning
- path planning
- vector valued
- loss function
- multiresolution
- learning environment
- humanoid robot
- multiscale