Knowledge Gradient for Online Reinforcement Learning.
Saba Q. YahyaaBernard ManderickPublished in: ICAART (Revised Selected Papers) (2014)
Keyphrases
- reinforcement learning
- expert systems
- knowledge base
- online learning
- decision making
- domain knowledge
- real time
- knowledge sharing
- learning algorithm
- knowledge extraction
- knowledge acquisition
- optimal policy
- complex domains
- knowledge transfer
- transfer learning
- learning systems
- higher level
- edge detection
- machine learning