Reinforcement learning and adaptive optimization of a class of Markov jump systems with completely unknown dynamic information.
Shuping HeMaoguang ZhangHaiyang FangFei LiuXiaoli LuanZhengtao DingPublished in: Neural Comput. Appl. (2020)
Keyphrases
- reinforcement learning
- computer systems
- information sources
- structural information
- dynamically changing
- end users
- information extraction
- markov chain
- contextual information
- dynamic environments
- information processing
- intelligent systems
- global optimization
- spatial information
- background knowledge
- machine learning
- distributed systems
- optimization problems
- domain knowledge
- expert systems
- information systems