Catastrophic Interference in Reinforcement Learning: A Solution Based on Context Division and Knowledge Distillation.
Tiantian ZhangXueqian WangBin LiangBo YuanPublished in: IEEE Trans. Neural Networks Learn. Syst. (2023)
Keyphrases
- reinforcement learning
- knowledge base
- contextual information
- domain knowledge
- knowledge acquisition
- global knowledge
- machine learning
- contextual knowledge
- linear equations
- closed form
- background knowledge
- wireless networks
- knowledge retrieval
- current situation
- conceptual model
- expert systems
- learning process
- state space
- optimal policy
- knowledge sources
- neural network
- artificial intelligence
- explicit knowledge
- learned knowledge
- prior knowledge
- function approximation
- knowledge management
- knowledge sharing
- mathematical model
- knowledge based systems
- domain experts
- data sets