Mordukhovich subgradients of the value function to a parametric discrete optimal control problem.
Nguyen Thi ToanJen-Chih YaoPublished in: J. Glob. Optim. (2014)
Keyphrases
- optimal control
- dynamic programming
- control problems
- optimal control problems
- risk sensitive
- feedback control
- class of nonlinear systems
- brownian motion
- reinforcement learning
- infinite horizon
- control strategy
- control law
- policy gradient
- neural network
- multistage
- lyapunov function
- continuous functions
- real time
- continuous stirred tank reactor