Revisiting Implicit Differentiation for Learning Problems in Optimal Control.
Ming XuTimothy L. MolloyStephen GouldPublished in: NeurIPS (2023)
Keyphrases
- optimal control
- learning problems
- reinforcement learning
- supervised learning
- learning tasks
- control problems
- machine learning algorithms
- dynamic programming
- learning algorithm
- kernel methods
- control strategy
- machine learning
- semi supervised learning
- infinite horizon
- optimal control problems
- pairwise
- mathematical model
- linear quadratic
- control system
- support vector
- decision trees
- image processing
- reproducing kernel hilbert space