Conservative Data Sharing for Multi-Task Offline Reinforcement Learning.
Tianhe YuAviral KumarYevgen ChebotarKarol HausmanSergey LevineChelsea FinnPublished in: NeurIPS (2021)
Keyphrases
- data sharing
- multi task
- reinforcement learning
- transfer learning
- multi task learning
- learning problems
- learning tasks
- data access
- data integration
- multitask learning
- multi class
- multiple tasks
- peer to peer
- information sharing
- gaussian processes
- feature selection
- learning algorithm
- sparse learning
- supervised learning
- learning process
- machine learning
- database
- data management
- information gain
- feature extraction
- prior knowledge
- information retrieval