Policy iteration-based optimal control design for nonlinear descriptor systems.
Yebin WangJing WuChengnian LongPublished in: ACC (2016)
Keyphrases
- optimal control
- policy iteration
- class of nonlinear systems
- infinite horizon
- dynamic programming
- optimal policy
- control strategy
- linear quadratic
- reinforcement learning
- least squares
- model free
- control problems
- approximate dynamic programming
- actor critic
- markov decision processes
- machine learning
- markov decision process
- cost function