Learning Gaussian Policies from Corrective Human Feedback.
Daan WoutJan ScholtenCarlos CeleminJens KoberPublished in: CoRR (2019)
Keyphrases
- learning systems
- motor skills
- language acquisition
- supervised learning
- online learning
- reinforcement learning
- prior knowledge
- learning algorithm
- human experts
- knowledge acquisition
- unsupervised learning
- maximum likelihood
- hierarchical reinforcement learning
- mobile learning
- mobile robot
- learning process
- multi agent
- artificial intelligence