mlsanityData to 7 Oct 2026

CW-ERM: Improving Autonomous Driving Planning with Closed-loop Weighted Empirical Risk Minimization

arXiv 2210.02174 ↗First posted 5 Oct 2022cs.LG cs.ROcited by 1

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

also in 1 more
Abstract (arXiv)

The imitation learning of self-driving vehicle policies through behavioral cloning is often carried out in an open-loop fashion, ignoring the effect of actions to future states. Training such policies purely with Empirical Risk Minimization (ERM) can be detrimental to real-world performance, as it biases policy networks towards matching only open-loop behavior, showing poor results when evaluated in closed-loop. In this work, we develop an efficient and simple-to-implement principle called Closed-loop Weighted Empirical Risk Minimization (CW-ERM), in which a closed-loop evaluation procedure is first used to identify training data samples that are important for practical driving performance and then we these samples to help debias the policy network. We evaluate CW-ERM in a challenging urban driving dataset and show that this procedure yields a significant reduction in collisions as well as other non-differentiable closed-loop metrics.

Key facts. Cited by 1 paper 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 22 of its 31 references that are in the map. First posted on arXiv 5 Oct 2022.

Builds on

22 of 31 references.

Closest ancestors · 1

Same direction, newest first

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

Other references · 21

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  4. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  5. 2016End to End Learning for Self-Driving Carscited by 1,000
  6. 2021Deep Reinforcement Learning at the Edge of the Statistical Precipicecited by 781
  7. 2019Argoverse: 3D Tracking and Forecasting with Rich Mapscited by 728
  8. 2021Large Scale Interactive Motion Forecasting for Autonomous Driving : The Waymo Open Motion Datasetcited by 532
  9. 2020VectorNet: Encoding HD Maps and Agent Dynamics from Vectorized Representationcited by 528
  10. 2021Just Train Twice: Improving Group Robustness without Training Group Informationcited by 522
  11. 2021NuPlan: A closed-loop ML-based planning benchmark for autonomous vehiclescited by 485
  12. 2017End-to-end Driving via Conditional Imitation Learningcited by 479
9 more
  1. 2018ChauffeurNet: Learning to Drive by Imitating the Best and Synthesizing the Worstcited by 391
  2. 2019Exploring the Limitations of Behavior Cloning for Autonomous Drivingcited by 343
  3. 2019Causal Confusion in Imitation Learningcited by 286
  4. 2016End-to-end Learning of Driving Models from Large-scale Video Datasetscited by 147
  5. 2017Imitating Driver Behavior with Generative Adversarial Networkscited by 92
  6. 2021SimNet: Learning Reactive Self-driving Simulations from Real-world Observationscited by 77
  7. 2021Feedback in Imitation Learning: The Three Regimes of Covariate Shiftcited by 68
  8. 2021SafetyNet: Safe planning for real-world self-driving vehicles using machine-learned policiescited by 68
  9. 2020Why resampling outperforms reweighting for correcting sampling bias with stochastic gradientscited by 34

Built on by

Cited by year

Citing papers per year: 2023: 1.

1 paper.

  1. 2023The Integration of Prediction and Planning in Deep Learning Automated Driving Systems: A Reviewcited by 29

Similar, not cited

Close in wording, no citation either way

  1. 2025From Imitation to Optimization: A Comparative Study of Offline Learning for Autonomous Driving
  2. 2025RoaD: Rollouts as Demonstrations for Closed-Loop Supervised Fine-Tuning of Autonomous Driving Policies
  3. 2022Learning from Demonstrations of Critical Driving Behaviours Using Driver's Risk Field
  4. 2024Data Scaling Laws for Imitation Learning-Based End-to-End Autonomous Driving
  5. 2026Imitation Learning for Autonomous Driving in CARLA
  6. 2025Exposing the Copycat Problem of Imitation-based Planner: A Novel Closed-Loop Simulator, Causal Benchmark and Joint IL-RL Baseline
  7. 2024IGDrivSim: A Benchmark for the Imitation Gap in Autonomous Driving
  8. 2026CRAFT: Counterfactual-to-Interactive Reinforcement Fine-Tuning for Driving Policies