mlsanityData to 7 Oct 2026

Verifiably Safe Exploration for End-to-End Reinforcement Learning

arXiv 2007.01223 ↗First posted 2 Jul 2020cs.AI cs.LG cs.LOcited by 32

Not on the map. Why?

Abstract (arXiv)

Deploying deep reinforcement learning in safety-critical settings requires developing algorithms that obey hard constraints during exploration. This paper contributes a first approach toward enforcing formal safety constraints on end-to-end policies with visual inputs. Our approach draws on recent advances in object detection and automated reasoning for hybrid dynamical systems. The approach is evaluated on a novel benchmark that emphasizes the challenge of safely exploring in the presence of hard constraints. Our benchmark draws from several proposed problem sets for safe learning and includes problems that emphasize challenges such as reward signals that are not aligned with safety constraints. On each of these benchmark problems, our algorithm completely avoids unsafe behavior while remaining competitive at optimizing for as much reward as is safe. We also prove that our method of enforcing the safety constraints preserves all safe policies from the original environment.

Key facts. Cited by 32 papers in the map (data through 7 Oct 2026). First posted on arXiv 2 Jul 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 12; 2023: 4; 2024: 4; 2025: 6; 2026: 4.

32 papers.

Sort:

By area:

  1. 2022A Review of Safe Reinforcement Learning: Methods, Theory and Applicationscited by 169
  2. 2022Exploration in Deep Reinforcement Learning: A Surveycited by 158
  3. 2021Exploration in Deep Reinforcement Learning: From Single-Agent to Multiagent Domaincited by 57
  4. 2023Safe Reinforcement Learning via Probabilistic Logic Shieldscited by 41
  5. 2021Enforcing Policy Feasibility Constraints through Differentiable Projection for Energy Optimizationcited by 31
  6. 2022Provably Safe Reinforcement Learning: Conceptual Analysis, Survey, and Benchmarkingcited by 31
  7. 2022Provably Safe Reinforcement Learning via Action Projection using Reachability Analysis and Polynomial Zonotopescited by 23
  8. 2022Online Shielding for Reinforcement Learningcited by 19
  9. 2022Provably Safe Deep Reinforcement Learning for Robotic Manipulation in Human Environmentscited by 16
  10. 2023A Human-Centered Safe Robot Reinforcement Learning Framework with Interactive Behaviorscited by 13
  11. 2022Dynamic Shielding for Reinforcement Learning in Black-Box Environmentscited by 11
  12. 2022LCRL: Certified Policy Synthesis via Logically-Constrained Reinforcement Learningcited by 11
20 more
  1. 2022Verified Probabilistic Policies for Deep Reinforcement Learningcited by 6
  2. 2023Reinforcement Learning with Knowledge Representation and Reasoning: A Brief Surveycited by 5
  3. 2025Safe Reinforcement Learning using Action Projection: Safeguard the Policy or the Environment?cited by 5
  4. 2022MLNav: Learning to Safely Navigate on Martian Terrainscited by 3
  5. 2024Safety-Driven Deep Reinforcement Learning Framework for Cobots: A Sim2Real Approachcited by 3
  6. 2022Ablation Study of How Run Time Assurance Impacts the Training and Performance of Reinforcement Learning Agentscited by 2
  7. 2023Runtime Verification of Learning Properties for Reinforcement Learning Algorithmscited by 2
  8. 2025A Provable Approach for End-to-End Safe Reinforcement Learningcited by 2
  9. 2025Safe and Compliant Cross-Market Trade Execution via Constrained RL and Zero-Knowledge Auditscited by 2
  10. 2025Provably Optimal Reinforcement Learning under Safety Filteringcited by 2
  11. 2026Any-Body Guard: Universal Safeguarding for Manipulation Policies via Action Maskingcited by 2
  12. 2024Towards Interpretable Reinforcement Learning with Constrained Normalizing Flow Policiescited by 1
  13. 2024Think Smart, Act SMARL! Analyzing Probabilistic Logic Shields for Multi-Agent Reinforcement Learningcited by 1
  14. 2025Predictive Safety Shield for Dyna-Q Reinforcement Learningcited by 1
  15. 2022GloCAL: Glocalized Curriculum-Aided Learning of Multiple Tasks with Application to Robotic Graspingcited by 0
  16. 2024Progressive Safeguards for Safe and Model-Agnostic Reinforcement Learningcited by 0
  17. 2025Game-Theoretic Risk-Shaped Reinforcement Learning for Safe Autonomous Drivingcited by 0
  18. 2026COOL-MC: Verifying and Explaining RL Policies for Platelet Inventory Managementcited by 0
  19. 2026COOL-MC: Verifying and Explaining RL Policies for Multi-bridge Network Maintenancecited by 0
  20. 2026Imagine to Ensure Safety in Hierarchical Reinforcement Learningcited by 0