A learner-verifier framework for neural network controllers and certificates of stochastic systems

DOI10.1007/978-3-031-30823-9_1MaRDI QIDQ6535337zbMATH OpenFDO

Authors Krishnendu Chatterjee, Thomas A. Henzinger, Mathias Lechner, Đorđe Žikelić

Publication date 13 December 2023

Copyright license Creative Commons Attribution 4.0 International

zbMATH Keywords

martingalesstochastic systemsformal verificationlearning-based control

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Specification and verification (program logics, model checking, etc.) (68Q60) Discrete-time control/observation systems (93C55) Stochastic systems in control theory (general) (93E03)

Recommendations

• Learning safe neural network controllers with barrier certificates
• Learning safe neural network controllers with barrier certificates
• Verisig
• Verifying Neural Network Controlled Systems Using Neural Networks

Cites work

• scientific article; zbMATH DE number 432503 (Why is no real title available?)
• scientific article; zbMATH DE number 1348599 (Why is no real title available?)
• scientific article; zbMATH DE number 700091 (Why is no real title available?)
• scientific article; zbMATH DE number 7559459 (Why is no real title available?)
• A Framework for Worst-Case and Stochastic Safety Verification Using Barrier Certificates
• A comprehensive survey on safe reinforcement learning
• A partial history of the early development of continuous-time nonlinear stochastic systems theory
• Algorithmic analysis of qualitative and quantitative termination problems for affine probabilistic programs
• Deductive proofs of almost sure persistence and recurrence properties
• FOSSIL
• Finding intrinsic rewards by embodied evolution and constrained reinforcement learning
• Learning probabilistic termination proofs
• Machine learning. A probabilistic perspective
• Model-Free Reinforcement Learning for Lexicographic Omega-Regular Objectives
• On Lexicographic Proof Rules for Probabilistic Termination
• Positive polynomials in control.
• Probability with Martingales
• SReachTools
• Sound and Complete Certificates for Quantitative Termination Analysis of Probabilistic Programs
• Stochastic invariants for probabilistic termination
• Stochastic optimal control via Bellman's principle.
• Termination analysis of probabilistic programs through Positivstellensatz's
• \textsf{AMYTISS}: parallelized automated controller synthesis for large-scale stochastic systems

Cited in

(8)

• Verisig 2.0: verification of neural network controllers using Taylor model preconditioning
• Brief Announcement
• Probabilistic reach-avoid for Bayesian neural networks
• Learning through imitation by using formal verification
• Learning safe neural network controllers with barrier certificates
• Verification-guided programmatic controller synthesis
• Verifiably Safe Off-Model Reinforcement Learning
• Risk verification of stochastic systems with neural network controllers

This page was built for publication: A learner-verifier framework for neural network controllers and certificates of stochastic systems

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6535337)