Model-free adaptive control design for nonlinear discrete-time processes with reinforcement learning techniques.
Dong LiuGuang-Hong YangPublished in: Int. J. Syst. Sci. (2018)
Keyphrases
- optimal policy
- reinforcement learning
- adaptive control
- model free
- policy iteration
- markov decision processes
- state space
- adaptive controller
- reinforcement learning algorithms
- variable structure
- average reward
- function approximation
- temporal difference
- nonlinear systems
- control problems
- dynamic programming
- feedback control
- learning algorithm
- machine learning
- optimal control
- rl algorithms
- learning problems
- learning process
- control method
- pose estimation
- markov chain