Verifiable Reinforcement Learning via Policy Extraction
Osbert Bastani, Yewen Pu, Armando Solar-Lezama
–Neural Information Processing Systems
DNNs, verifying these properties is typically very inefficient if not infeasible [6].
Neural Information Processing Systems
Nov-21-2025, 03:57:01 GMT
- Country:
- North America
- Canada > Quebec
- Montreal (0.04)
- United States
- California (0.04)
- Massachusetts > Middlesex County
- Cambridge (0.04)
- Canada > Quebec
- North America
- Technology:
- Information Technology > Artificial Intelligence
- Machine Learning
- Decision Tree Learning (0.76)
- Neural Networks (0.70)
- Reinforcement Learning (1.00)
- Representation & Reasoning (1.00)
- Robots (1.00)
- Machine Learning
- Information Technology > Artificial Intelligence