Learning Retrospective Knowledge with Reverse Reinforcement Learning.
Shangtong ZhangVivek VeeriahShimon WhitesonPublished in: NeurIPS (2020)
Keyphrases
- reinforcement learning
- learning process
- learned knowledge
- knowledge acquisition
- supervised learning
- learning algorithm
- effective learning
- learning problems
- learning systems
- learning tasks
- function approximation
- concept maps
- prior knowledge
- background knowledge
- online learning
- knowledge representation
- knowledge transfer
- organizational learning
- knowledge level
- complex domains
- previously learned
- domain experts
- collaborative learning
- action selection
- active learning
- temporal difference learning