Learning Domain Randomization Distributions for Training Robust Locomotion Policies.
Melissa MozifianJuan Camilo Gamboa HigueraDavid MegerGregory DudekPublished in: IROS (2020)
Keyphrases
- learning algorithm
- supervised learning
- learning process
- prior knowledge
- online learning
- unsupervised learning
- learning speed
- learning problems
- domain independent
- machine learning
- domain specific
- learning systems
- training process
- domain adaptation
- reinforcement learning
- online training
- dynamic programming
- active learning
- training examples
- training set
- feature space
- training phase
- learning machines
- computer based training
- minimum error rate