mlsanityData to 7 Oct 2026

How to Learn from Risk: Explicit Risk-Utility Reinforcement Learning for Efficient and Safe Driving Strategies

arXiv 2203.08409 ↗First posted 16 Mar 2022cs.LGcited by 4

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

Abstract (arXiv)

Autonomous driving has the potential to revolutionize mobility and is hence an active area of research. In practice, the behavior of autonomous vehicles must be acceptable, i.e., efficient, safe, and interpretable. While vanilla reinforcement learning (RL) finds performant behavioral strategies, they are often unsafe and uninterpretable. Safety is introduced through Safe RL approaches, but they still mostly remain uninterpretable as the learned behaviour is jointly optimized for safety and performance without modeling them separately. Interpretable machine learning is rarely applied to RL. This paper proposes SafeDQN, which allows to make the behavior of autonomous vehicles safe and interpretable while still being efficient. SafeDQN offers an understandable, semantic trade-off between the expected risk and the utility of actions while being algorithmically transparent. We show that SafeDQN finds interpretable and safe driving policies for a variety of scenarios and demonstrate how state-of-the-art saliency techniques can help to assess both risk and utility.

Key facts. Cited by 4 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 37 references that are in the map. First posted on arXiv 16 Mar 2022.

Builds on

19 of 37 references.

References · 19

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2017Axiomatic Attribution for Deep Networkscited by 3,350
  3. 2017CARLA: An Open Urban Driving Simulatorcited by 2,431
  4. 2015Deep Reinforcement Learning with Double Q-learningcited by 1,704
  5. 2017Constrained Policy Optimizationcited by 928
  6. 2017Rainbow: Combining Improvements in Deep Reinforcement Learningcited by 774
  7. 2016The Mythos of Model Interpretabilitycited by 716
  8. 2017Safe Reinforcement Learning via Shieldingcited by 427
  9. 2018Reward Constrained Policy Optimizationcited by 397
  10. 2016European Union regulations on algorithmic decision-making and a "right to explanation"cited by 343
  11. 2020Responsive Safety in Reinforcement Learning by PID Lagrangian Methodscited by 302
  12. 2018Safe Exploration in Continuous Action Spacescited by 237
7 more
  1. 2020A Survey on the Explainability of Supervised Machine Learningcited by 225
  2. 2020Conservative Safety Critics for Explorationcited by 107
  3. 2019Combining Planning and Deep Reinforcement Learning in Tactical Decision Making for Autonomous Drivingcited by 52
  4. 2018Automated Speed and Lane Change Decision Making using Deep Reinforcement Learningcited by 36
  5. 2020Automated Lane Change Strategy using Proximal Policy Optimization-based Deep Reinforcement Learningcited by 30
  6. 2022An Introduction to Multi-Agent Reinforcement Learning and Review of its Application to Autonomous Mobilitycited by 16
  7. 2020Reinforcement Learning with Uncertainty Estimation for Tactical Decision-Making in Intersectionscited by 15

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 0; 2024: 1; 2025: 1; 2026: 1.

4 papers.

  1. 2022Driver Dojo: A Benchmark for Generalizable Reinforcement Learning for Autonomous Drivingcited by 2
  2. 2025Risk-Aware Reinforcement Learning for Autonomous Driving: Improving Safety When Driving through Intersectioncited by 2
  3. 2024Act Better by Timing: A timing-Aware Reinforcement Learning for Autonomous Drivingcited by 1
  4. 2026Constrained Reinforcement Learning Using Successor Representationscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Balancing Progress and Safety: A Novel Risk-Aware Objective for RL in Autonomous Driving
  2. 2025AED: Automatic Discovery of Effective and Diverse Vulnerabilities for Autonomous Driving Policy with Large Language Models
  3. 2022Automatically Learning Fallback Strategies with Model-Free Reinforcement Learning in Safety-Critical Driving Scenarios
  4. 2025VLM-SAFE: Vision-Language Model-Guided Safety-Aware Reinforcement Learning with World Models for Autonomous Driving
  5. 2022SafeRL-Kit: Evaluating Efficient Reinforcement Learning Methods for Safe Autonomous Driving
  6. 2021Minimizing Safety Interference for Safe and Comfortable Automated Driving with Distributional Reinforcement Learning
  7. 2025Learning Safe Autonomous Driving Policies Using Predictive Safety Representations
  8. 2024Long and Short-Term Constraints Driven Safe Reinforcement Learning for Autonomous Driving