mlsanityData to 7 Oct 2026

Safe Reinforcement Learning for Autonomous Vehicles through Parallel Constrained Policy Optimization

arXiv 2003.01303 ↗First posted 3 Mar 2020cs.LG cs.AI stat.MLcited by 34

Not on the map. Why?

Abstract (arXiv)

Reinforcement learning (RL) is attracting increasing interests in autonomous driving due to its potential to solve complex classification and control problems. However, existing RL algorithms are rarely applied to real vehicles for two predominant problems: behaviours are unexplainable, and they cannot guarantee safety under new scenarios. This paper presents a safe RL algorithm, called Parallel Constrained Policy Optimization (PCPO), for two autonomous driving tasks. PCPO extends today's common actor-critic architecture to a three-component learning framework, in which three neural networks are used to approximate the policy function, value function and a newly added risk function, respectively. Meanwhile, a trust region constraint is added to allow large update steps without breaking the monotonic improvement condition. To ensure the feasibility of safety constrained problems, synchronized parallel learners are employed to explore different state spaces, which accelerates learning and policy-update. The simulations of two scenarios for autonomous vehicles confirm we can ensure safety while achieving fast learning.

Key facts. Cited by 34 papers in the map (data through 7 Oct 2026). First posted on arXiv 3 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: 9; 2023: 5; 2024: 7; 2025: 6; 2026: 3.

34 papers.

Sort:

By area:

  1. 2022A Review of Safe Reinforcement Learning: Methods, Theory and Applicationscited by 169
  2. 2023CAT: Closed-loop Adversarial Training for Safe End-to-End Drivingcited by 52
  3. 2021Achieving Zero Constraint Violation for Constrained Reinforcement Learning via Primal-Dual Approachcited by 46
  4. 2022Provably Efficient Risk-Sensitive Reinforcement Learning: Iterated CVaR and Worst Pathcited by 21
  5. 2022Achieving Zero Constraint Violation for Constrained Reinforcement Learning via Conservative Natural Policy Gradient Primal-Dual Algorithmcited by 19
  6. 2024Learning Adversarial MDPs with Stochastic Hard Constraintscited by 15
  7. 2023Provably Efficient Iterated CVaR Reinforcement Learning with Function Approximation and Human Feedbackcited by 13
  8. 2022Spatial-Temporal-Aware Safe Multi-Agent Reinforcement Learning of Connected Autonomous Vehicles in Challenging Scenarioscited by 12
  9. 2024Optimal Strong Regret and Violation in Constrained MDPs via Policy Optimizationcited by 11
  10. 2024RACER: Epistemic Risk-Sensitive RL Enables Fast Driving with Fewer Crashescited by 10
  11. 2023A Best-of-Both-Worlds Algorithm for Constrained MDPs with Long-Term Constraintscited by 9
  12. 2022Multi-task Safe Reinforcement Learning for Navigating Intersections in Dense Trafficcited by 7
22 more
  1. 2022SafeRL-Kit: Evaluating Efficient Reinforcement Learning Methods for Safe Autonomous Drivingcited by 6
  2. 2023Provably Efficient CVaR RL in Low-rank MDPscited by 6
  3. 2021Provably Correct Training of Neural Network Controllers Using Reachability Analysiscited by 5
  4. 2024Learning Constrained Markov Decision Processes With Non-stationary Rewards and Constraintscited by 5
  5. 2021Improved Robustness and Safety for Pre-Adaptation of Meta Reinforcement Learning with Prior Regularizationcited by 4
  6. 2024Confident Natural Policy Gradient for Local Planning in qπ-realizable Constrained MDPscited by 4
  7. 2026Regret Analysis of Unichain Average Reward Constrained MDPs with General Parameterizationcited by 4
  8. 2021Quick Learner Automated Vehicle Adapting its Roadmanship to Varying Traffic Cultures with Meta Reinforcement Learningcited by 3
  9. 2022Safe Reinforcement Learning with Contrastive Risk Predictioncited by 3
  10. 2022Improve Generalization of Driving Policy at Signalized Intersections with Adversarial Learningcited by 2
  11. 2025A Survey of Reinforcement Learning-Based Motion Planning for Autonomous Driving: Lessons Learned from a Driving Task Perspectivecited by 2
  12. 2022A Safety-Critical Decision Making and Control Framework Combining Machine Learning and Rule-based Algorithmscited by 1
  13. 2024Pre-Trained Vision Models as Perception Backbones for Safety Filters in Autonomous Drivingcited by 1
  14. 2025Assuring the Safety of Reinforcement Learning Components: AMLAS-RLcited by 1
  15. 2025Beyond Slater's Condition in Online CMDPs with Stochastic and Adversarial Constraintscited by 1
  16. 2023How to ensure a safe control strategy? Towards a SRL for urban transit autonomous operationcited by 0
  17. 2024A novel agent with formal goal-reaching guarantees: an experimental study with a mobile robotcited by 0
  18. 2025Safety Modulation: Enhancing Safety in Reinforcement Learning through Cost-Modulated Rewardscited by 0
  19. 2025A Domain-Based Taxonomy of Jailbreak Vulnerabilities in Large Language Modelscited by 0
  20. 2025Skill-based Safe Reinforcement Learning with Risk Planningcited by 0
  21. 2026Artificial Intelligence for Modeling and Simulation of Mixed Automated and Human Trafficcited by 0
  22. 2026Safe Greenhouse Climate Control Using Lagrangian-Constrained PPO with Kolmogorov-Arnold Networkscited by 0