Output Feedback Tube MPC-Guided Data Augmentation for Robust, Efficient Sensorimotor Policy Learning.
Andrea TagliabueJonathan P. HowPublished in: IROS (2022)
Keyphrases
- data sets
- data collection
- data analysis
- learning process
- learning models
- online learning
- input data
- database
- data structure
- prior knowledge
- data points
- human experts
- raw data
- missing data
- learning systems
- end users
- data sources
- reinforcement learning
- dynamic model
- action selection
- language acquisition
- learning tasks
- supervised learning
- relevance feedback
- learning algorithm
- machine learning