Output Feedback Reinforcement Q-learning for Optimal Quadratic Tracking Control of Unknown Discrete-Time Linear Systems and Its Application.
Guangyue ZhaoWeijie SunHe CaiYunjian PengPublished in: ICARCV (2018)
Keyphrases
- linear systems
- tracking control
- reinforcement learning
- dynamical systems
- sufficient conditions
- dynamic programming
- nonlinear systems
- control law
- learning algorithm
- learning rate
- optimal control
- state space
- objective function
- sparse linear systems
- experimental data
- optimization algorithm
- interior point methods
- real time