Learning Barrier Certificates: Towards Safe Reinforcement Learning with Zero Training-time Violations.
Yuping LuoTengyu MaPublished in: NeurIPS (2021)
Keyphrases
- reinforcement learning
- supervised learning
- learning process
- learning algorithm
- online learning
- learning problems
- active learning
- learning tasks
- machine learning
- prior knowledge
- active exploration
- evolutionary learning
- recurrent networks
- action selection
- multi agent
- training data
- learning systems
- structured prediction
- learning stage
- computer based training
- relational reinforcement learning
- decision trees