Catastrophic Interference in Reinforcement Learning: A Solution Based on Context Division and Knowledge Distillation.
Tiantian ZhangXueqian WangBin LiangBo YuanPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- knowledge base
- optimal solution
- global knowledge
- domain knowledge
- data mining techniques
- contextual knowledge
- knowledge retrieval
- linear equations
- function approximation
- contextual information
- learning systems
- knowledge sources
- background knowledge
- learning algorithm
- prior knowledge
- expert systems
- knowledge based systems
- closed form
- conceptual model
- knowledge management
- user model
- context sensitive
- conceptual framework
- state space
- action selection
- complex domains
- knowledge representation
- information systems