Safe Reinforcement Learning via Probabilistic Logic Shields.
Wen-Chi YangGiuseppe MarraGavin RensLuc De RaedtPublished in: NeSy (2023)
Keyphrases
- probabilistic logic
- reinforcement learning
- maximum entropy
- probabilistic reasoning
- default reasoning
- statistical relational learning
- abductive reasoning
- cp logic
- probability theory
- state space
- machine learning
- probabilistic knowledge
- image segmentation
- learning algorithm
- dynamic programming
- artificial neural networks
- partial order
- computational intelligence
- probability distribution
- rationality postulates
- neural network