mlsanityData to 7 Oct 2026

Cautious Reinforcement Learning with Logical Constraints

arXiv 2002.12156 ↗First posted 26 Feb 2020cs.LG cs.AI cs.LOcited by 44

Not on the map. Why?

Abstract (arXiv)

This paper presents the concept of an adaptive safe padding that forces Reinforcement Learning (RL) to synthesise optimal control policies while ensuring safety during the learning process. Policies are synthesised to satisfy a goal, expressed as a temporal logic formula, with maximal probability. Enforcing the RL agent to stay safe during learning might limit the exploration, however we show that the proposed architecture is able to automatically handle the trade-off between efficient progress in exploration (towards goal satisfaction) and ensuring safety. Theoretical guarantees are available on the optimality of the synthesised policies and on the convergence of the learning algorithm. Experimental results are provided to showcase the performance of the proposed method.

Key facts. Cited by 44 papers in the map (data through 7 Oct 2026). First posted on arXiv 26 Feb 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 4; 2022: 13; 2023: 10; 2024: 9; 2025: 2; 2026: 6.

44 papers.

Sort:

By area:

  1. 2022A Review of Safe Reinforcement Learning: Methods, Theory and Applicationscited by 169
  2. 2021Safe Multi-Agent Reinforcement Learning via Shieldingcited by 60
  3. 2022Safe Reinforcement Learning via Shielding under Partial Observabilitycited by 49
  4. 2024A Survey of Constraint Formulations in Safe Reinforcement Learningcited by 42
  5. 2021Modular Deep Reinforcement Learning for Continuous Motion Planning with Temporal Logiccited by 38
  6. 2022Provably Safe Reinforcement Learning: Conceptual Analysis, Survey, and Benchmarkingcited by 31
  7. 2022Safe Reinforcement Learning for Legged Locomotioncited by 29
  8. 2022Provably Safe Reinforcement Learning via Action Projection using Reachability Analysis and Polynomial Zonotopescited by 23
  9. 2022Learning Control Policies for Stochastic Systems with Reach-avoid Guaranteescited by 21
  10. 2022Online Shielding for Reinforcement Learningcited by 19
  11. 2023ALLURE: Auditing and Improving LLM-based Evaluation of Text using Iterative In-Context-Learningcited by 15
  12. 2021Shielding Atari Games with Bounded Presciencecited by 14
32 more
  1. 2024Safe Reinforcement Learning on the Constraint Manifold: Theory and Applicationscited by 12
  2. 2022Dynamic Shielding for Reinforcement Learning in Black-Box Environmentscited by 11
  3. 2022LCRL: Certified Policy Synthesis via Logically-Constrained Reinforcement Learningcited by 11
  4. 2023Model-based Dynamic Shielding for Safe and Efficient Multi-Agent Reinforcement Learningcited by 11
  5. 2021Reinforcement Learning with External Knowledge by using Logical Neural Networkscited by 10
  6. 2022Correct-by-Construction Runtime Enforcement in AI -- A Surveycited by 10
  7. 2023Shielded Reinforcement Learning for Hybrid Systemscited by 8
  8. 2022Verified Probabilistic Policies for Deep Reinforcement Learningcited by 6
  9. 2023Reinforcement Learning with Knowledge Representation and Reasoning: A Brief Surveycited by 5
  10. 2022Reinforcement Learning Guided by Provable Normative Compliancecited by 3
  11. 2022Logic-based Reward Shaping for Multi-Agent Reinforcement Learningcited by 3
  12. 2023Safe and Sample-efficient Reinforcement Learning for Clustered Dynamic Environmentscited by 3
  13. 2024Optimal Transport-Assisted Risk-Sensitive Q-Learningcited by 3
  14. 2023System III: Learning with Domain Knowledge for Safety Constraintscited by 2
  15. 2023Reinforcement Learning Under Probabilistic Spatio-Temporal Constraints with Time Windowscited by 2
  16. 2024Composing Reinforcement Learning Policies, with Formal Guaranteescited by 2
  17. 2024Tractable Offline Learning of Regular Decision Processescited by 2
  18. 2026Shields to Guarantee Probabilistic Safety in MDPscited by 2
  19. 2023Safeguarded Progress in Reinforcement Learning: Safe Bayesian Exploration for Control Policy Synthesiscited by 1
  20. 2024Concurrent Learning of Policy and Unknown Safety Constraints in Reinforcement Learningcited by 1
  21. 2024Multi-agent transformer-accelerated RL for satisfaction of STL specificationscited by 1
  22. 2024Probabilistic Satisfaction of Temporal Logic Constraints in Reinforcement Learning via Adaptive Policy-Switchingcited by 1
  23. 2025Predictive Safety Shield for Dyna-Q Reinforcement Learningcited by 1
  24. 2023Constrained Exploration in Reinforcement Learning with Optimality Preservationcited by 0
  25. 2023SCPO: Safe Reinforcement Learning with Safety Critic Policy Optimizationcited by 0
  26. 2024Progressive Safeguards for Safe and Model-Agnostic Reinforcement Learningcited by 0
  27. 2025Hyperproperty-Constrained Secure Reinforcement Learningcited by 0
  28. 2026LANTERN: LLM-Augmented Neurosymbolic Transfer with Experience-Gated Reasoning Networkscited by 0
  29. 2026Auditing Near-Optimal Policies Can Be Exponentially Hard: Conditional Query Lower Bounds via Occupancy Rashomon Capacitycited by 0
  30. 2026Formal Verification of Learned Multi-Agent Communication Policies via Decision Tree Distillationcited by 0
  31. 2026SafeExplorer: An Unbiased Policy Gradient for Reinforcement Learning with Recovery Interventionscited by 0
  32. 2026Efficient Bayes-Adaptive Reinforcement Learning with Temporal Logic Specificationscited by 0