Reinforcement learning for linear exponential quadratic Gaussian problem.
Jing LaiJunlin XiongPublished in: Syst. Control. Lett. (2024)
Keyphrases
- reinforcement learning
- linear complexity
- linear computational complexity
- function approximators
- function approximation
- taylor series expansion
- quadratic function
- state space
- dynamic programming
- pairwise
- learning algorithm
- linear quadratic
- closed form
- semidefinite
- neural network
- learning process
- nonlinear functions
- linear functions
- linear constraints
- optimal control
- markov decision processes
- temporal difference
- learning problems
- multi agent systems
- linear filters
- objective function
- differential operators
- multiscale
- gaussian mixture model
- supervised learning
- gaussian convolution
- linear gaussian
- machine learning