Value-Gradient Based Formulation of Optimal Control Problem and Machine Learning Algorithm.
Alain BensoussanJiayue HanSheung Chi Phillip YamXiang ZhouPublished in: SIAM J. Numer. Anal. (2023)
Keyphrases
- optimal control
- learning algorithm
- reinforcement learning
- dynamic programming
- control problems
- feedback control
- class of nonlinear systems
- control strategy
- risk sensitive
- infinite horizon
- rl algorithms
- back propagation
- brownian motion
- neural network
- optimal control problems
- lyapunov function
- control law
- learning problems
- model free
- machine learning
- real time