Reward Learning from Suboptimal Demonstrations with Applications in Surgical Electrocautery.
Zohre KarimiShing-Hei HoBao ThachAlan KuntzDaniel S. BrownPublished in: ISMR (2024)
Keyphrases
- learning process
- reinforcement learning
- online learning
- supervised learning
- learning algorithm
- learning problems
- virtual reality
- active learning
- hidden markov models
- prior knowledge
- knowledge acquisition
- unsupervised learning
- artificial neural networks
- mobile learning
- neural network
- incremental learning
- inverse reinforcement learning