Multi-step heuristic dynamic programming for optimal control of nonlinear discrete-time systems.
Biao LuoDerong LiuTingwen HuangXiong YangHongwen MaPublished in: Inf. Sci. (2017)
Keyphrases
- optimal control
- dynamic programming
- multi step
- linear quadratic
- optimal control problems
- class of nonlinear systems
- control problems
- lyapunov function
- infinite horizon
- feedback control
- lower bounding
- reinforcement learning
- continuous stirred tank reactor
- control strategy
- knapsack problem
- linear programming
- state space
- linear systems
- markov decision processes
- neural network