Bias-policy iteration based optimal control for unknown continuous-time linear periodic systems.
Xiang LiHuaiyuan JiangBin ZhouPublished in: Syst. Control. Lett. (2024)
Keyphrases
- optimal control
- policy iteration
- infinite horizon
- dynamic programming
- control problems
- control strategy
- optimal control problems
- markov decision processes
- average cost
- reinforcement learning
- linear quadratic
- brownian motion
- actor critic
- linear systems
- approximate dynamic programming
- state space
- markov decision process
- average reward