Multi-policy Grounding and Ensemble Policy Learning for Transfer Learning with Dynamics Mismatch.
Hyun-Rok LeeRam Ananth SreenivasanYeonjeong JeongJongseong JangDongsub ShimChi-Guhn LeePublished in: IJCAI (2022)
Keyphrases
- transfer learning
- learning tasks
- learning algorithm
- knowledge transfer
- transfer knowledge
- active learning
- reinforcement learning
- learning process
- multi task learning
- optimal policy
- domain adaptation
- semi supervised
- supervised learning
- multi task
- cross domain
- knowledge sharing
- previously learned
- labeled data
- multitask learning
- sample selection bias
- solve complex tasks
- dynamical systems
- machine learning algorithms
- training samples
- unlabeled data
- unsupervised learning
- domain specific
- decision trees