Learning Multi-Task Transferable Rewards via Variational Inverse Reinforcement Learning.
Se-Wook YooSeung-Woo SeoPublished in: ICRA (2022)
Keyphrases
- multi task
- inverse reinforcement learning
- multi task learning
- learning tasks
- learning problems
- multiple tasks
- reinforcement learning
- learning algorithm
- learning process
- active learning
- supervised learning
- partially observable environments
- machine learning
- partially observable
- transfer learning
- semi supervised
- hidden variables
- utility function
- unsupervised learning
- prior knowledge