A reinforcement learning-based scheme for adaptive optimal control of linear stochastic systems.
Wee Chin WongJay H. LeePublished in: ACC (2008)
Keyphrases
- optimal control
- stochastic systems
- reinforcement learning
- control problems
- linear quadratic
- actor critic
- dynamic programming
- stochastic models
- control strategy
- adaptive control
- infinite horizon
- control law
- average cost
- sample path
- learning algorithm
- model free
- function approximation
- markov decision processes
- asymptotic analysis
- machine learning
- confidence intervals
- real time
- function approximators
- optimal policy
- policy gradient
- state space