Revisiting Implicit Differentiation for Learning Problems in Optimal Control.
Ming XuTimothy MolloyStephen GouldPublished in: CoRR (2023)
Keyphrases
- learning problems
- optimal control
- reinforcement learning
- learning tasks
- dynamic programming
- control problems
- supervised learning
- machine learning
- learning algorithm
- machine learning algorithms
- kernel methods
- infinite horizon
- optimal control problems
- control strategy
- semi supervised learning
- pairwise
- semi supervised
- state space
- function approximation
- reproducing kernel hilbert space
- unsupervised learning
- neural network
- reinforcement learning algorithms
- training data