An iterative scheme of safe reinforcement learning for nonlinear systems via barrier certificate generation

DOI10.1007/978-3-030-81685-8_22zbMath1493.68224OpenAlexW3185438801MaRDI QIDQ832198

Yidan Zhang, Xia Zeng, Zhengfeng Yang, Zhenbing Zeng, Xiaochao Tang, Wang Lin, Zhi-Ming Liu

Publication date: 25 March 2022

Full work available at URL: https://doi.org/10.1007/978-3-030-81685-8_22

zbMATH Keywords

formal verificationcontinuous dynamical systemsbarrier certificatessafe reinforcement learning

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Nonlinear systems in control theory (93C10) Specification and verification (program logics, model checking, etc.) (68Q60)

Related Items (1)

Learning through imitation by using formal verification

Uses Software

• PENBMI
• GitHub
• nncontroller
• Sherlock
• ReachNN

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Construction of parametric barrier functions for dynamical systems using interval analysis
• Stability and stabilization of polynomial dynamical systems using Bernstein polynomials
• Reachability analysis for neural feedback systems using regressive polynomial rule inference
• Verisig
• Sherlock - A tool for verification of neural network feedback systems
• Nonlinear Control Synthesis by Convex Optimization
• Computing Output Feedback Controllers to Enlarge the Domain of Attraction in Polynomial Systems
• A Framework for Worst-Case and Stochastic Safety Verification Using Barrier Certificates
• Learning safe neural network controllers with barrier certificates

This page was built for publication: An iterative scheme of safe reinforcement learning for nonlinear systems via barrier certificate generation