mlsanityData to 7 Oct 2026

Exploring the trade off between human driving imitation and safety for traffic simulation

arXiv 2208.04803 ↗First posted 9 Aug 2022cs.LG cs.ROcited by 3

On the map: End-to-end autonomous driving → Imitation-learning end-to-end planners

Abstract (arXiv)

Traffic simulation has gained a lot of interest for quantitative evaluation of self driving vehicles performance. In order for a simulator to be a valuable test bench, it is required that the driving policy animating each traffic agent in the scene acts as humans would do while maintaining minimal safety guarantees. Learning the driving policies of traffic agents from recorded human driving data or through reinforcement learning seems to be an attractive solution for the generation of realistic and highly interactive traffic situations in uncontrolled intersections or roundabouts. In this work, we show that a trade-off exists between imitating human driving and maintaining safety when learning driving policies. We do this by comparing how various Imitation learning and Reinforcement learning algorithms perform when applied to the driving task. We also propose a multi objective learning algorithm (MOPPO) that improves both objectives together. We test our driving policies on highly interactive driving scenarios extracted from INTERACTION Dataset to evaluate how human-like they behave.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Placed in Imitation-learning end-to-end planners, one of 9 directions in End-to-end autonomous driving. Builds on 31 of its 40 references that are in the map. First posted on arXiv 9 Aug 2022.

Builds on

31 of 40 references.

Closest ancestors · 1

Same direction, newest first

  1. 2021Urban Driver: Learning to Drive from Real-world Demonstrations Using Policy Gradients27 Sep

Other references · 30

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2015High-Dimensional Continuous Control Using Generalized Advantage Estimationcited by 1,916
  3. 2016Generative Adversarial Imitation Learningcited by 1,576
  4. 2020Gradient Surgery for Multi-Task Learningcited by 1,210
  5. 2018Multi-Task Learning as Multi-Objective Optimizationcited by 809
  6. 2017Learning Robust Rewards with Adversarial Inverse Reinforcement Learningcited by 485
  7. 2017End-to-end Driving via Conditional Imitation Learningcited by 479
  8. 2019Exploring the Limitations of Behavior Cloning for Autonomous Drivingcited by 343
  9. 2019Causal Confusion in Imitation Learningcited by 286
  10. 2021MetaDrive: Composing Diverse Driving Scenarios for Generalizable Reinforcement Learningcited by 281
  11. 2019INTERACTION Dataset: An INTERnational, Adversarial and Cooperative moTION Dataset in Interactive Driving Scenarios with Semantic Mapscited by 231
  12. 2018Discriminator-Actor-Critic: Addressing Sample Inefficiency and Reward Bias in Adversarial Imitation Learningcited by 203
18 more
  1. 2021TrafficSim: Learning to Simulate Realistic Multi-Agent Behaviorscited by 192
  2. 2014Qualitatively characterizing neural network optimization problemscited by 186
  3. 2020Can Autonomous Vehicles Identify, Recover From, and Adapt to Distribution Shifts?cited by 139
  4. 2021Generating Useful Accident-Prone Driving Scenarios via a Learned Traffic Priorcited by 136
  5. 2021Reward (Mis)design for Autonomous Drivingcited by 102
  6. 2019Model-free Deep Reinforcement Learning for Urban Autonomous Drivingcited by 96
  7. 2017Imitating Driver Behavior with Generative Adversarial Networkscited by 92
  8. 2021SafetyNet: Safe planning for real-world self-driving vehicles using machine-learned policiescited by 68
  9. 2018Multi-Agent Imitation Learning for Driving Simulationcited by 49
  10. 2021Efficient Deep Reinforcement Learning with Imitative Expert Priors for Autonomous Drivingcited by 46
  11. 2019Task-Relevant Adversarial Imitation Learningcited by 45
  12. 2021Improved Deep Reinforcement Learning with Expert Demonstrations for Urban Autonomous Drivingcited by 26
  13. 2018Learning from Demonstration in the Wildcited by 25
  14. 2019Simulating Emergent Properties of Human Driving Behavior Using Multi-Agent Reward Augmented Imitation Learningcited by 24
  15. 2021Human-in-the-Loop Deep Reinforcement Learning with Application to Autonomous Drivingcited by 16
  16. 2021Building Safer Autonomous Agents by Leveraging Risky Driving Behavior Knowledgecited by 4
  17. 2021Towards Learning Generalizable Driving Policies from Restricted Latent Representationscited by 4
  18. 2022A Safety-Critical Decision Making and Control Framework Combining Machine Learning and Rule-based Algorithmscited by 1

Built on by

Cited by year

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

3 papers.

  1. 2024LASIL: Learner-Aware Supervised Imitation Learning For Long-term Microscopic Traffic Simulationcited by 7
  2. 2025DecompGAIL: Learning Realistic Traffic Behaviors with Decomposed Multi-Agent Generative Adversarial Imitation Learningcited by 5
  3. 2023Long-term Microscopic Traffic Simulation with History-Masked Multi-agent Imitation Learningcited by 2

Similar, not cited

Close in wording, no citation either way

  1. 2022Imitation Is Not Enough: Robustifying Imitation with Reinforcement Learning for Challenging Driving Scenarios
  2. 2022Learning from Demonstrations of Critical Driving Behaviours Using Driver's Risk Field
  3. 2023Learning Realistic Traffic Agents in Closed-loop
  4. 2021Iterative Imitation Policy Improvement for Interactive Autonomous Driving
  5. 2021Safe Imitation Learning on Real-Life Highway Data for Human-like Autonomous Driving
  6. 2025Learning to Drive by Imitating Surrounding Vehicles
  7. 2024Human-compatible driving partners through data-regularized self-play reinforcement learning
  8. 2022SHAIL: Safety-Aware Hierarchical Adversarial Imitation Learning for Autonomous Driving in Urban Environments