mlsanityData to 7 Oct 2026

SafeRL-Kit: Evaluating Efficient Reinforcement Learning Methods for Safe Autonomous Driving

arXiv 2206.08528 ↗First posted 17 Jun 2022cs.LG cs.AI cs.ROcited by 6

On the map: End-to-end autonomous driving → Reinforcement learning for driving

Abstract (arXiv)

Safe reinforcement learning (RL) has achieved significant success on risk-sensitive tasks and shown promise in autonomous driving (AD) as well. Considering the distinctiveness of this community, efficient and reproducible baselines are still lacking for safe AD. In this paper, we release SafeRL-Kit to benchmark safe RL methods for AD-oriented tasks. Concretely, SafeRL-Kit contains several latest algorithms specific to zero-constraint-violation tasks, including Safety Layer, Recovery RL, off-policy Lagrangian method, and Feasible Actor-Critic. In addition to existing approaches, we propose a novel first-order method named Exact Penalty Optimization (EPO) and sufficiently demonstrate its capability in safe AD. All algorithms in SafeRL-Kit are implemented (i) under the off-policy setting, which improves sample efficiency and can better leverage past logs; (ii) with a unified learning framework, providing off-the-shelf interfaces for researchers to incorporate their domain-specific knowledge into fundamental safe RL methods. Conclusively, we conduct a comparative evaluation of the above algorithms in SafeRL-Kit and shed light on their efficacy for safe autonomous driving. The source code is available at href https://github.com/zlr20/saferlkitthis https URL.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Placed in Reinforcement learning for driving, one of 9 directions in End-to-end autonomous driving. Builds on 19 of its 27 references that are in the map. First posted on arXiv 17 Jun 2022.

Builds on

19 of 27 references.

Closest ancestors · 2

Same direction, newest first

  1. 2022Efficient Learning of Safe Driving Policy via Human-AI Copilot Optimization17 Feb
  2. 2021MetaDrive: Composing Diverse Driving Scenarios for Generalizable Reinforcement Learning26 Sep

Other references · 17

  1. 2018Addressing Function Approximation Error in Actor-Critic Methodscited by 2,302
  2. 2016Concrete Problems in AI Safetycited by 1,582
  3. 2017Constrained Policy Optimizationcited by 928
  4. 2020Deep Reinforcement Learning for Autonomous Driving: A Surveycited by 698
  5. 2015Risk-Constrained Reinforcement Learning with Percentile Risk Criteriacited by 320
  6. 2018Safe Exploration in Continuous Action Spacescited by 237
  7. 2020Recovery RL: Safe Reinforcement Learning with Learned Recovery Zonescited by 156
  8. 2020Learning to Walk in the Real World with Minimal Human Effortcited by 103
  9. 2019Safe Policies for Reinforcement Learning via Primal-Dual Methodscited by 75
  10. 2022Penalized Proximal Policy Optimization for Safe Reinforcement Learningcited by 60
  11. 2019Safe Reinforcement Learning on Autonomous Vehiclescited by 48
  12. 2021safe-control-gym: a Unified Benchmark Suite for Safe Learning-based Control and Reinforcement Learning in Roboticscited by 42
5 more
  1. 2020Safe Reinforcement Learning for Autonomous Vehicles through Parallel Constrained Policy Optimizationcited by 34
  2. 2021Feasible Actor-Critic: Constrained Reinforcement Learning for Ensuring Statewise Safetycited by 30
  3. 2022Safe Reinforcement Learning for Legged Locomotioncited by 29
  4. 2021Learn-to-Race: A Multimodal Control Environment for Autonomous Racingcited by 23
  5. 2021Safe Autonomous Racing via Approximate Reachability on Ego-visioncited by 13

Built on by

Cited by year

Citing papers per year: 2023: 3; 2024: 2; 2025: 1.

6 papers.

  1. 2023GUARD: A Safe Reinforcement Learning Benchmarkcited by 13
  2. 2023State-wise Constrained Policy Optimizationcited by 9
  3. 2024Long and Short-Term Constraints Driven Safe Reinforcement Learning for Autonomous Drivingcited by 4
  4. 2023Human-AI Collaboration in Real-World Complex Environment with Reinforcement Learningcited by 2
  5. 2024Absolute State-wise Constrained Policy Optimization: High-Probability State-wise Constraints Satisfactioncited by 0
  6. 2025Barrier Function Overrides For Non-Convex Fixed Wing Flight Control and Self-Driving Carscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2021Minimizing Safety Interference for Safe and Comfortable Automated Driving with Distributional Reinforcement Learning
  2. 2025Balancing Progress and Safety: A Novel Risk-Aware Objective for RL in Autonomous Driving
  3. 2022How to Learn from Risk: Explicit Risk-Utility Reinforcement Learning for Efficient and Safe Driving Strategies
  4. 2024Latent Safety-Constrained Policy Approach for Safe Offline Reinforcement Learning
  5. 2025Learning Safe Autonomous Driving Policies Using Predictive Safety Representations
  6. 2026Safe Reinforcement Learning of Autonomous Highway Driving: A Unified Framework for Safety and Efficiency
  7. 2023Datasets and Benchmarks for Offline Safe Reinforcement Learning
  8. 2025Safety Reinforced Model Predictive Control (SRMPC): Improving MPC with Reinforcement Learning for Motion Planning in Autonomous Driving