Incremental Adaptive Dynamic Programming for Approximate Optimal Tracking Control: a Decoupled and Model-Free Approach.
Cong LiYongchao WangFangzhou LiuMartin BussPublished in: CoRR (2021)
Keyphrases
- model free
- dynamic programming
- tracking control
- reinforcement learning
- policy evaluation
- adaptive neural
- policy iteration
- optimal control
- function approximation
- markov decision processes
- temporal difference
- control law
- nonlinear systems
- optimal policy
- adaptive control
- state space
- neural network
- control system
- artificial neural networks
- supervised learning
- data mining