Learning task-parametrized assistive strategies for exoskeleton robots by multi-task reinforcement learning.
Masashi HamayaTakamitsu MatsubaraTomoyuki NodaTatsuya TeramaeJun MorimotoPublished in: ICRA (2017)
Keyphrases
- multi task
- reinforcement learning
- multi task learning
- learning tasks
- learning problems
- learning process
- learning algorithm
- multiple tasks
- multitask learning
- autonomous robots
- prior knowledge
- machine learning algorithms
- transfer learning
- high order
- learning models
- active learning
- learning environment
- unsupervised learning
- mutual information
- supervised learning
- probabilistic model
- gaussian processes
- mobile robot