Model-based and model-free designs for an extended continuous-time LQR with exogenous inputs.
Sayak MukherjeeHe BaiAranya ChakraborttyPublished in: Syst. Control. Lett. (2021)
Keyphrases
- model free
- reinforcement learning
- optimal control
- function approximation
- reinforcement learning algorithms
- policy iteration
- temporal difference
- state space
- policy evaluation
- markov chain
- radial basis function
- learning algorithm
- neural network
- autoregressive
- learning experience
- dynamic programming
- control system
- machine learning