Deep adaptive dynamic programming for nonaffine nonlinear optimal control problem with state constraints.
Jingliang DuanZhengyu LiuShengbo Eben LiQi SunZhenzhong JiaBo ChengPublished in: CoRR (2019)
Keyphrases
- optimal control
- dynamic programming
- class of nonlinear systems
- state space
- linear quadratic
- lyapunov function
- control problems
- risk sensitive
- control law
- feedback control
- infinite horizon
- multistage
- control strategy
- optimal control problems
- continuous stirred tank reactor
- actor critic
- brownian motion
- markov decision processes
- optimal policy
- reinforcement learning
- linear constraints
- greedy algorithm
- neural network controller
- learning algorithm
- real time