Online Adaptive Optimal Control of Discrete-time Linear Systems via Synchronous Q-learning.
Xinxing LiXueyuan WangWenzhong ZhaPublished in: SMC (2021)
Keyphrases
- optimal control
- linear systems
- optimal control problems
- reinforcement learning
- dynamical systems
- linear quadratic
- control theory
- actor critic
- dynamic programming
- sufficient conditions
- state space
- control problems
- feedback control
- policy iteration
- sparse linear systems
- adaptive control
- function approximation
- infinite horizon
- control law
- numerical solution
- reinforcement learning algorithms
- learning algorithm
- control strategy
- model free
- real time
- optimal policy
- learning rate
- linear programming
- objective function
- interior point methods
- markov chain
- coefficient matrix
- neural network