An iterative scheme for the approximate linear programming solution to the optimal control of a Markov Decision Process.
Alessandro FalsoneMaria PrandiniPublished in: ECC (2015)
Keyphrases
- optimal control
- linear programming
- dynamic programming
- optimal control problems
- optimal solution
- control problems
- exact solution
- control strategy
- risk sensitive
- class of nonlinear systems
- hamilton jacobi bellman
- feedback control
- quadratic programming
- mathematical model
- brownian motion
- linear program
- infinite horizon
- lyapunov function
- markov decision processes
- column generation
- machine learning
- optimal policy