A Unified Framework for Alternating Offline Model Training and Policy Learning.
Shentao YangShujian ZhangYihao FengMingyuan ZhouPublished in: NeurIPS (2022)
Keyphrases
- prior knowledge
- learning models
- structured prediction
- computational model
- learning algorithm
- probability distribution
- learning mechanism
- training phase
- online learning
- learning speed
- machine learning
- learning tasks
- learning systems
- training examples
- graphical models
- supervised learning
- objective function
- reinforcement learning