Temporal logic guided safe model-based reinforcement learning: a hybrid systems approach

DOI10.1016/j.nahs.2022.101295zbMath1505.93116OpenAlexW4306783402MaRDI QIDQ2677109

Calin Belta, Max H. Cohen, Kevin Leahy, Zachary Serlin

Publication date: 13 January 2023

Published in: Nonlinear Analysis. Hybrid Systems (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.nahs.2022.101295

zbMATH Keywords

adaptive controlreinforcement learningLyapunov methodsapproximate dynamic programmingtemporal logics

Mathematics Subject Classification ID

Nonlinear systems in control theory (93C10) Adaptive control/observation systems (93C40) Temporal logic (03B44) Control/observation systems governed by functional relations other than differential equations (such as hybrid and switching systems) (93C30)

Related Items

Fault-tolerant control based on reinforcement learning and sliding event-triggered mechanism for a class of unknown discrete-time systems

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Efficient model-based reinforcement learning for approximate online optimal control
• Model-based reinforcement learning for approximate optimal regulation
• Online actor-critic algorithm to solve the continuous-time infinite horizon optimal control problem
• Adaptive nonlinear control without overparametrization
• Switching in systems and control
• Reinforcement learning for optimal feedback control. A Lyapunov-based approach
• A novel actor-critic-identifier architecture for approximate optimal control of uncertain nonlinear systems
• Data-based reinforcement learning approximate optimal control for an uncertain nonlinear system with control effectiveness faults
• Deep reinforcement learning with temporal logics
• Formal methods for discrete-time dynamical systems
• Safe exploration in model-based reinforcement learning using control barrier functions
• LTL receding horizon control for finite deterministic systems
• Approximate optimal influence over an agent through an uncertain interaction dynamic
• Communication-Free Multi-Agent Control Under Local Temporal Tasks and Relative-Distance Constraints
• Verification and Control of Hybrid Systems
• Control Barrier Function Based Quadratic Programs for Safety Critical Systems
• A Fully Automated Framework for Control of Linear Systems from Temporal Logic Specifications
• Integral concurrent learning: Adaptive control with parameter convergence using finite excitation
• Dynamical properties of hybrid automata
• Sampling-based Approximate Optimal Control Under Temporal Logic Constraints
• Linear Time Logic Control of Discrete-Time Linear Systems
• Synthesis of Reactive Switching Protocols From Temporal Logic Specifications
• Concurrent Learning for Parameter Estimation Using Dynamic State-Derivative Estimators
• Reinforcement Learning and Feedback Control: Using Natural Decision Methods to Design Optimal Adaptive Controllers
• Formal Techniques, Modelling and Analysis of Timed and Fault-Tolerant Systems
• Satisfaction of Linear Temporal Logic Specifications Through Recurrence Tools for Hybrid Systems