Generalized constraint for probabilistic safe reinforcement learning.
Weiqin ChenSantiago PaternainPublished in: L4DC (2024)
Keyphrases
- reinforcement learning
- newly defined
- function approximation
- bayesian networks
- optimal policy
- dual space
- probabilistic logic
- reinforcement learning algorithms
- uncertain data
- generative model
- machine learning
- markov decision processes
- state space
- model free
- learning process
- learning algorithm
- data driven
- context sensitive
- active learning
- temporal difference
- learning environment
- bayes rule
- multi agent