Off-policy reinforcement learning for tracking control of discrete-time Markov jump linear systems with completely unknown dynamics.
Zhen HuangYidong TuHaiyang FangHai WangLiang ZhangKaibo ShiShuping HePublished in: J. Frankl. Inst. (2023)
Keyphrases
- linear systems
- tracking control
- markov chain
- dynamical systems
- state space
- reinforcement learning
- control law
- nonlinear systems
- adaptive control
- tracking error
- sparse linear systems
- adaptive neural
- dynamic programming
- sufficient conditions
- interior point methods
- basis functions
- closed loop
- fuzzy model
- lyapunov function
- learning algorithm
- particle filter
- fuzzy systems
- particle swarm optimization
- multi objective
- expert systems
- support vector
- knowledge base
- neural network