Learning Barrier Certificates: Towards Safe Reinforcement Learning with Zero Training-time Violations.
Yuping LuoTengyu MaPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- learning process
- supervised learning
- learning speed
- autonomous learning
- learning problems
- online learning
- feedforward neural networks
- machine learning
- learning algorithm
- structured prediction
- reinforcement learning methods
- temporal difference learning
- learning systems
- online training
- knowledge acquisition
- active learning
- neural network
- minimum error rate
- learning stage
- unsupervised learning
- access control
- multi agent