Distill Knowledge in Multi-task Reinforcement Learning with Optimal-Transport Regularization.
Bang Giang LeViet Cuong TaPublished in: CoRR (2023)
Keyphrases
- multi task
- reinforcement learning
- multi task learning
- penalty term
- learning problems
- learning tasks
- knowledge discovery
- multi class
- group lasso
- multitask learning
- markov random field
- sparse learning
- feature selection
- multiple tasks
- gaussian processes
- transfer learning
- prior knowledge
- learning process
- pairwise
- image segmentation