A learner-verifier framework for neural network controllers and certificates of stochastic systems
From MaRDI portal
Publication:6535337
DOI10.1007/978-3-031-30823-9_1zbMath1545.93589MaRDI QIDQ6535337
Đorđe Žikelić, Mathias Lechner, Thomas A. Henzinger, Krishnendu Chatterjee
Publication date: 13 December 2023
Learning and adaptive systems in artificial intelligence (68T05) Discrete-time control/observation systems (93C55) Specification and verification (program logics, model checking, etc.) (68Q60) Stochastic systems in control theory (general) (93E03)
Cites Work
- Learning probabilistic termination proofs
- Stochastic optimal control via Bellman's principle.
- Positive polynomials in control.
- Finding intrinsic rewards by embodied evolution and constrained reinforcement learning
- \textsf{AMYTISS}: parallelized automated controller synthesis for large-scale stochastic systems
- Deductive proofs of almost sure persistence and recurrence properties
- 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
- Probability with Martingales
- Termination Analysis of Probabilistic Programs Through Positivstellensatz’s
- SReachTools
- A Framework for Worst-Case and Stochastic Safety Verification Using Barrier Certificates
- Stochastic invariants for probabilistic termination
- FOSSIL
- Sound and Complete Certificates for Quantitative Termination Analysis of Probabilistic Programs
- Model-Free Reinforcement Learning for Lexicographic Omega-Regular Objectives
- On Lexicographic Proof Rules for Probabilistic Termination
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
This page was built for publication: A learner-verifier framework for neural network controllers and certificates of stochastic systems
