Online Safety Assurance for Deep Reinforcement Learning.
Noga H. RotmanMichael SchapiraAviv TamarPublished in: CoRR (2020)
Keyphrases
- reinforcement learning
- online learning
- markov decision processes
- real time
- optimal policy
- machine learning
- learning process
- state space
- function approximation
- robotic control
- multi agent reinforcement learning
- batch mode
- information security
- learning problems
- supervised learning
- active learning
- decision trees
- data mining