Follow the Clairvoyant: an Imitation Learning Approach to Optimal Control.
Andrea MartinLuca FurieriFlorian DörflerJohn LygerosGiancarlo Ferrari-TrecatePublished in: CoRR (2022)
Keyphrases
- optimal control
- imitation learning
- reinforcement learning
- control problems
- dynamic programming
- robotic systems
- reinforcement learning methods
- humanoid robot
- optimal control problems
- maximum margin
- control strategy
- infinite horizon
- learning algorithm
- machine learning
- function approximation
- state space
- model free
- vision system
- concept learning
- control law
- probabilistic model
- policy iteration
- control system