Safe Reinforcement Learning: Learning with Supervision Using a Constraint-Admissible Set.
Zhaojian LiUros KalabicTianshu ChuPublished in: ACC (2018)
Keyphrases
- reinforcement learning
- learning process
- active learning
- learning systems
- learning algorithm
- small number
- state space
- prior knowledge
- multi agent
- supervised learning
- unsupervised learning
- machine learning
- learning problems
- active exploration
- probability distribution
- knowledge acquisition
- markov decision processes
- positive examples
- linear constraints