Learning to Recover for Safe Reinforcement Learning.
Haoyu WangXin YuanQinqing RenPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- learning process
- supervised learning
- active learning
- learning systems
- learning problems
- unsupervised learning
- learning capabilities
- machine learning
- learning agents
- learned knowledge
- partially observable
- knowledge acquisition
- inductive inference
- function approximation
- reinforcement learning methods
- learning community
- learning tasks
- markov decision processes
- online learning
- state space
- learning algorithm
- genetic algorithm