Policy iteration based feedback control.
Kan-Jian ZhangYan-Kai XuXi ChenXi-Ren CaoPublished in: Autom. (2008)
Keyphrases
- feedback control
- policy iteration
- optimal control
- markov decision processes
- infinite horizon
- reinforcement learning
- closed loop
- adaptive control
- model free
- fixed point
- sample path
- dynamic programming
- least squares
- optimal policy
- policy evaluation
- control strategy
- finite state
- markov decision process
- average reward
- markov decision problems
- control law
- state space
- temporal difference
- linear programming
- machine learning
- control system
- multistage
- markov chain