Safe Off-policy Reinforcement Learning Using Barrier Functions.
Zahra MarviBahare KiumarsiPublished in: ACC (2020)
Keyphrases
- reinforcement learning
- function approximation
- machine learning
- artificial intelligence
- learning process
- basis functions
- temporal difference
- clustering algorithm
- data sets
- state space
- active learning
- temporal difference learning
- optimal control
- monte carlo
- optimal policy
- supervised learning
- case study
- website
- databases