Policy Iteration for Optimal Control of Discrete-Time Time-Varying Nonlinear Systems.
Guangyu ZhuXiaolu LiRanran SunYiyuan YangPeng ZhangPublished in: IEEE CAA J. Autom. Sinica (2023)
Keyphrases
- optimal control
- nonlinear systems
- policy iteration
- control law
- optimal control problems
- dead zone
- infinite horizon
- control strategy
- control problems
- adaptive control
- dynamic programming
- reinforcement learning
- adaptive neural
- lyapunov function
- approximate dynamic programming
- feedback control
- fuzzy model
- learning rate
- finite state
- fuzzy control
- fuzzy controller
- markov decision processes
- fuzzy systems
- markov chain
- actor critic
- sliding mode
- fixed point
- average cost
- mathematical model
- markov decision process
- model free
- average reward
- markov processes
- optimal policy
- control scheme
- control algorithm
- stochastic control
- neural network
- lyapunov stability
- hamilton jacobi bellman
- temporal difference
- production planning
- genetic algorithm