Reset-Free Reinforcement Learning via Multi-Task Learning: Learning Dexterous Manipulation Behaviors without Human Intervention.
Abhishek GuptaJustin YuTony Z. ZhaoVikash KumarAaron RovinskyKelvin XuThomas DevlinSergey LevinePublished in: CoRR (2021)
Keyphrases
- multi task learning
- reinforcement learning
- learning problems
- learning tasks
- multi task
- multiple tasks
- learning process
- learning algorithm
- transfer learning
- multitask learning
- prior knowledge
- unsupervised learning
- knowledge acquisition
- supervised learning
- gaussian processes
- state space
- previously learned
- learning experience
- machine learning
- inductive learning
- bayesian networks
- multi label image annotation