Reinforced Model Predictive Control via Trust-Region Quasi-Newton Policy Optimization.
Dean BrandnerSergio LuciaPublished in: ECC (2024)
Keyphrases
- quasi newton
- trust region
- newton method
- optimization methods
- convergence analysis
- optimization method
- linear equations
- regularized least squares
- variational inequalities
- optimality conditions
- quadratic programming
- global optimum
- global convergence
- step size
- differential evolution
- optimization problems
- particle swarm
- machine learning
- simulated annealing
- state space
- artificial neural networks