Off-policy algorithm based Hierarchical optimal control for completely unknown dynamic systems.
Xiaohong CuiJiayu ChenBinrui WangSuan XuPublished in: Neurocomputing (2022)
Keyphrases
- dynamic systems
- optimal control
- dynamic programming
- learning algorithm
- knapsack problem
- complex systems
- objective function
- state variables
- mathematical model
- linear programming
- image restoration
- expectation maximization
- np hard
- search space
- cooperative
- nonlinear systems
- qualitative reasoning
- control problems
- consistency based diagnosis