Sample Complexity of the Linear Quadratic Regulator: A Reinforcement Learning Lens.
Amirreza Neshaei MoghaddamAlex OlshevskyBahman GharesifardPublished in: CoRR (2024)
Keyphrases
- linear quadratic
- sample complexity
- optimal control
- reinforcement learning
- learning problems
- learning algorithm
- supervised learning
- closed loop
- theoretical analysis
- dynamical systems
- vector valued
- upper bound
- active learning
- generalization error
- dynamic programming
- special case
- lower bound
- training examples
- machine learning
- gaussian model
- state space
- control strategy
- small number
- data sets
- sample size
- learning tasks
- optimal policy
- training samples
- unsupervised learning
- reproducing kernel hilbert space
- probabilistic model
- computational complexity