Safe Reinforcement Learning Using Probabilistic Shields (Invited Paper).
Nils JansenBettina KönighoferSebastian JungesAlex SerbanRoderick BloemPublished in: CONCUR (2020)
Keyphrases
- invited paper
- reinforcement learning
- reinforcement learning algorithms
- machine learning
- function approximation
- state space
- learning algorithm
- bayesian networks
- generative model
- optimal policy
- uncertain data
- data mining
- multi agent
- mobile robot
- databases
- markov decision processes
- probabilistic logic
- poster session
- real world