mlsanityData to 7 Oct 2026

On Robustness Metrics for Learning STL Tasks

arXiv 2003.06041 ↗First posted 12 Mar 2020eess.SY cs.SYcited by 27

Not on the map. Why?

Abstract (arXiv)

Signal temporal logic (STL) is a powerful tool for describing complex behaviors for dynamical systems. Among many approaches, the control problem for systems under STL task constraints is well suited for learning-based solutions, because STL is equipped with robustness metrics that quantify the satisfaction of task specifications and thus serve as useful rewards. In this work, we examine existing and potential robustness metrics specifically from the perspective of how they can aid such learning algorithms. We show that various desirable properties restrict the form of potential metrics, and introduce a new one based on the results. The effectiveness of this new robustness metric for accelerating the learning procedure is demonstrated through an insightful case study.

Key facts. Cited by 27 papers in the map (data through 7 Oct 2026). First posted on arXiv 12 Mar 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 4; 2022: 5; 2023: 6; 2024: 4; 2025: 2; 2026: 6.

27 papers.

Sort:

By area:

  1. 2022Provably Safe Reinforcement Learning: Conceptual Analysis, Survey, and Benchmarkingcited by 31
  2. 2023Logic of Differentiable Logics: Towards a Uniform Semantics of DLcited by 15
  3. 2021Model-Free Reinforcement Learning for Optimal Control of MarkovDecision Processes Under Signal Temporal Logic Specificationscited by 10
  4. 2024ULLER: A Unified Language for Learning and Reasoningcited by 9
  5. 2024TLINet: Differentiable Neural Network Temporal Logic Inferencecited by 8
  6. 2023Learning Robust and Correct Controllers from Signal Temporal Logic Specifications Using BarrierNetcited by 6
  7. 2021STL Robustness Risk over Discrete-Time Stochastic Processescited by 4
  8. 2022Interpretable Fault Diagnosis of Rolling Element Bearings with Temporal Logic Neural Networkcited by 4
  9. 2022STL-Based Synthesis of Feedback Controllers Using Reinforcement Learningcited by 4
  10. 2021Safe Model-based Control from Signal Temporal Logic Specifications Using Recurrent Neural Networkscited by 3
  11. 2022Model Predictive Robustness of Signal Temporal Logic Predicatescited by 3
  12. 2023Requirement falsification for cyber-physical systems using generative modelscited by 3
15 more
  1. 2021Neural Network-based Control for Multi-Agent Systems from Spatio-Temporal Specificationscited by 2
  2. 2022Differentiable Logics for Neural Network Training and Verificationcited by 1
  3. 2023A Safe Preference Learning Approach for Personalization with Applications to Autonomous Vehiclescited by 1
  4. 2023Comparing Differentiable Logics for Learning Systems: A Research Previewcited by 1
  5. 2024Learning to Estimate System Specifications in Linear Temporal Logic using Transformers and Mambacited by 1
  6. 2025A General Framework for Property-Driven Machine Learningcited by 1
  7. 2026Conformal Signal Temporal Logic for Robust Reinforcement Learning Control: A Case Studycited by 1
  8. 2026Spatiotemporal Robustness of Temporal Logic Tasks using Multi-Objective Reasoningcited by 1
  9. 2023Learning Modulo Theoriescited by 0
  10. 2024Autonomous Vehicles Path Planning under Temporal Logic Specificationscited by 0
  11. 2025Feasibility-aware Learning of Robust Temporal Logic Controllers using BarrierNetcited by 0
  12. 2026Quantitative Linear Logic for Neuro-Symbolic Learning and Verificationcited by 0
  13. 2026Robustness of Robotic Manipulation: Foundations and Frontierscited by 0
  14. 2026Reward Machines for Signal Temporal Logiccited by 0
  15. 2026Backward through Time, Algebraicallycited by 0