mlsanityData to 7 Oct 2026

Safe Reinforcement Learning on Autonomous Vehicles

arXiv 1910.00399 ↗First posted 27 Sep 2019cs.LG cs.AI cs.ROcited by 48

Not on the map. Why?

Abstract (arXiv)

There have been numerous advances in reinforcement learning, but the typically unconstrained exploration of the learning process prevents the adoption of these methods in many safety critical applications. Recent work in safe reinforcement learning uses idealized models to achieve their guarantees, but these models do not easily accommodate the stochasticity or high-dimensionality of real world systems. We investigate how prediction provides a general and intuitive framework to constraint exploration, and show how it can be used to safely learn intersection handling behaviors on an autonomous vehicle.

Key facts. Cited by 48 papers in the map (data through 7 Oct 2026). First posted on arXiv 27 Sep 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 7; 2022: 9; 2023: 8; 2024: 8; 2025: 10; 2026: 6.

48 papers.

Sort:

By area:

  1. 2022A Review of Safe Reinforcement Learning: Methods, Theory and Applicationscited by 169
  2. 2021A Survey of Deep RL and IL for Autonomous Driving Policy Learningcited by 59
  3. 2023CAT: Closed-loop Adversarial Training for Safe End-to-End Drivingcited by 52
  4. 2021How to Certify Machine Learning Based Safety-critical Systems? A Systematic Literature Reviewcited by 36
  5. 2022Provably Safe Reinforcement Learning via Action Projection using Reachability Analysis and Polynomial Zonotopescited by 23
  6. 2023Constraint-Conditioned Policy Optimization for Versatile Safe Reinforcement Learningcited by 17
  7. 2022State Dropout-Based Curriculum Reinforcement Learning for Self-Driving at Unsignalized Intersectionscited by 15
  8. 2024Learning Adversarial MDPs with Stochastic Hard Constraintscited by 15
  9. 2023Active Uncertainty Reduction for Safe and Efficient Interaction Planning: A Shielding-Aware Dual Control Approachcited by 13
  10. 2023GUARD: A Safe Reinforcement Learning Benchmarkcited by 13
  11. 2023Provably Efficient Iterated CVaR Reinforcement Learning with Function Approximation and Human Feedbackcited by 13
  12. 2025A Survey of Safe Reinforcement Learning and Constrained MDPs: A Technical Survey on Single-Agent and Multi-Agent Safetycited by 12
36 more
  1. 2024Optimal Strong Regret and Violation in Constrained MDPs via Policy Optimizationcited by 11
  2. 2025CurricuVLM: Towards Safe Autonomous Driving via Personalized Safety-Critical Curriculum Learning with Vision-Language Modelscited by 11
  3. 2021A Survey of Deep Reinforcement Learning Algorithms for Motion Planning and Control of Autonomous Vehiclescited by 10
  4. 2022Spatiotemporal Costmap Inference for MPC via Deep Inverse Reinforcement Learningcited by 10
  5. 2023A Best-of-Both-Worlds Algorithm for Constrained MDPs with Long-Term Constraintscited by 9
  6. 2021Minimizing Safety Interference for Safe and Comfortable Automated Driving with Distributional Reinforcement Learningcited by 8
  7. 2022Multi-task Safe Reinforcement Learning for Navigating Intersections in Dense Trafficcited by 7
  8. 2023Gradient Shaping for Multi-Constraint Safe Reinforcement Learningcited by 7
  9. 2024Autonomous Driving at Unsignalized Intersections: A Review of Decision-Making Challenges and Reinforcement Learning-Based Solutionscited by 7
  10. 2022SafeRL-Kit: Evaluating Efficient Reinforcement Learning Methods for Safe Autonomous Drivingcited by 6
  11. 2023Provably Efficient CVaR RL in Low-rank MDPscited by 6
  12. 2024Learning Constrained Markov Decision Processes With Non-stationary Rewards and Constraintscited by 5
  13. 2025An Optimistic Algorithm for online CMDPS with Anytime Adversarial Constraintscited by 5
  14. 2024Adversarially Trained Weighted Actor-Critic for Safe Offline Reinforcement Learningcited by 4
  15. 2024Safety Optimized Reinforcement Learning via Multi-Objective Policy Optimizationcited by 4
  16. 2024Critic as Lyapunov function (CALF): a model-free, stability-ensuring agentcited by 4
  17. 2021Safe Deep Q-Network for Autonomous Vehicles at Unsignalized Intersectioncited by 3
  18. 2022A Verification Framework for Certifying Learning-Based Safety-Critical Aviation Systemscited by 3
  19. 2025Geometry of Neural Reinforcement Learning in Continuous State and Action Spacescited by 3
  20. 2021Pedestrian Collision Avoidance for Autonomous Vehicles at Unsignalized Intersection Using Deep Q-Networkcited by 2
  21. 2022A Safety-Critical Decision Making and Control Framework Combining Machine Learning and Rule-based Algorithmscited by 1
  22. 2025Predictive Response Optimization: Using Reinforcement Learning to Fight Online Social Network Abusecited by 1
  23. 2025SPoRt -- Safe Policy Ratio: Certified Training and Deployment of Task Policies in Model-Free RLcited by 1
  24. 2025Action Space Reduction Strategies for Reinforcement Learning in Autonomous Drivingcited by 1
  25. 2025Beyond Slater's Condition in Online CMDPs with Stochastic and Adversarial Constraintscited by 1
  26. 2026Learning Weakly Communicating Average-Reward CMDPs: Strong Duality and Improved Regretcited by 1
  27. 2021A Policy Efficient Reduction Approach to Convex Constrained Deep Reinforcement Learningcited by 0
  28. 2022Data Valuation for Offline Reinforcement Learningcited by 0
  29. 2024mathrmE2CFD: Towards Effective and Efficient Cost Function Design for Safe Reinforcement Learning via Large Language Modelcited by 0
  30. 2025Enhancing Offline Reinforcement Learning with Curriculum Learning-Based Trajectory Valuationcited by 0
  31. 2025Goal-conditioned Hierarchical Reinforcement Learning for Sample-efficient and Safe Autonomous Driving at Intersectionscited by 0
  32. 2026STO-RL: Offline RL under Sparse Rewards via LLM-Guided Subgoal Temporal Ordercited by 0
  33. 2026Primal-Dual Policy Optimization for Linear CMDPs with Adversarial Lossescited by 0
  34. 2026Individual Control Barrier Functions-Guided Diffusion Model for Safe Offline Multi-Agent Reinforcement Learningcited by 0
  35. 2026Scaling Learning-based AEB with Massive Unlabeled Datacited by 0
  36. 2026Artificial Intelligence and Modeling & Simulation: An Overviewcited by 0