Discrete-Time Nonlinear HJB Solution Using Approximate Dynamic Programming: Convergence Proof.
Asma Al-TamimiFrank L. LewisMurad Abu-KhalafPublished in: IEEE Trans. Syst. Man Cybern. Part B (2008)
Keyphrases
- approximate dynamic programming
- hamilton jacobi bellman
- actor critic
- convergence proof
- linear program
- optimal control
- reinforcement learning
- dynamic programming
- control policy
- markov chain
- step size
- control problems
- linear programming
- policy iteration
- model checking
- mathematical model
- particle swarm optimization
- stochastic control
- optimal solution