Adaptive Optimal Control for a Class of Nonlinear Systems: The Online Policy Iteration Approach.
Shuping HeHaiyang FangMaoguang ZhangFei LiuZhengtao DingPublished in: IEEE Trans. Neural Networks Learn. Syst. (2020)
Keyphrases
- optimal control
- class of nonlinear systems
- policy iteration
- infinite horizon
- actor critic
- control problems
- dynamic programming
- reinforcement learning
- approximate dynamic programming
- control strategy
- policy evaluation
- markov decision processes
- markov decision problems
- optimal control problems
- average reward
- average cost
- real time
- markov decision process
- genetic algorithm
- search space
- function approximation
- linear program
- monte carlo
- multistage
- optimal policy
- simulated annealing
- learning algorithm
- data mining