A Unified Framework for Alternating Offline Model Training and Policy Learning.
Shentao YangShujian ZhangYihao FengMingyuan ZhouPublished in: CoRR (2022)
Keyphrases
- learning mechanism
- mathematical model
- supervised learning
- computational model
- learning scheme
- online learning
- learning algorithm
- learning models
- probabilistic model
- reinforcement learning
- similarity measure
- prior knowledge
- training set
- machine learning
- probability distribution
- learning tasks
- learning problems
- training algorithm
- learning phase
- learned models
- recurrent networks
- training program