Verifiably safe exploration for end-to-end reinforcement learning

DOI10.1145/3447928.3456653arXiv2007.01223OpenAlexW3159199672MaRDI QIDQ6201597

Sara Magliacane, Unnamed Author, Armando Solar-Lezama, Subhro Das, Unnamed Author, Nathan Fulton

Publication date: 21 February 2024

Published in: Proceedings of the 24th International Conference on Hybrid Systems: Computation and Control (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2007.01223

zbMATH Keywords

hybrid systemsneural networksformal verificationreinforcement learningdifferential dynamic logicsafe artificial intelligence

Mathematics Subject Classification ID

Formal languages and automata (68Q45) Specification and verification (program logics, model checking, etc.) (68Q60) Control/observation systems governed by functional relations other than differential equations (such as hybrid and switching systems) (93C30)

Cites Work

• ModelPlex: verified runtime validation of verified cyber-physical system models
• Differential dynamic logic for hybrid systems
• Bellerophon: tactical theorem proving for hybrid systems
• A complete uniform substitution calculus for differential dynamic logic
• Deep reinforcement learning with temporal logics
• Logics of Dynamical Systems
• A Uniform Substitution Calculus for Differential Dynamic Logic
• KeYmaera X: An Axiomatic Tactical Theorem Prover for Hybrid Systems
• The Image Computation Problem in Hybrid Systems Model Checking
• Handbook of Model Checking
• Logical Analysis of Hybrid Systems
• Unnamed Item
• Unnamed Item
• Unnamed Item

This page was built for publication: Verifiably safe exploration for end-to-end reinforcement learning