H∞ Tracking learning control for discrete-time Markov jump systems: A parallel off-policy reinforcement learning.
Xuewen ZhangJianwei XiaJing WangXiangyong ChenHao ShenPublished in: J. Frankl. Inst. (2023)
Keyphrases
- reinforcement learning
- learning systems
- markov chain
- learning process
- learning algorithm
- learning problems
- robot control
- control problems
- supervised learning
- online learning
- optimal control
- complex systems
- real time
- learning tasks
- control strategies
- control method
- computer systems
- particle filter
- distributed systems
- autonomous robots
- action selection
- markov processes
- control strategy
- function approximation
- control system
- temporal difference
- human operators
- multi agent
- bayesian networks
- autonomous learning