mlsanityData to 7 Oct 2026

Distributionally Robust Imitation Learning: Layered Control Architecture for Certifiable Autonomy

arXiv 2512.17899 ↗First posted 19 Dec 2025eess.SY cs.LG cs.SYcited by 1

On the map: Offline RL and imitation learning from data → Imitation learning methods

Abstract (arXiv)

Imitation learning (IL) enables autonomous behavior by learning from expert demonstrations. While more sample-efficient than comparative alternatives like reinforcement learning, IL is sensitive to compounding errors induced by distribution shifts. There are two significant sources of distribution shifts when using IL-based feedback laws on systems: distribution shifts caused by policy error and distribution shifts due to exogenous disturbances and endogenous model errors due to lack of learning. Our previously developed approaches, Taylor Series Imitation Learning (TaSIL) and L1 -Distributionally Robust Adaptive Control (ellonedrac), address the challenge of distribution shifts in complementary ways. While TaSIL offers robustness against policy error-induced distribution shifts, ellonedrac offers robustness against distribution shifts due to aleatoric and epistemic uncertainties. To enable certifiable IL for learned and/or uncertain dynamical systems, we formulate textitDistributionally Robust Imitation Policy (DRIP) architecture, a Layered Control Architecture (LCA) that integrates TaSIL and~ellonedrac. By judiciously designing individual layer-centric input and output requirements, we show how we can guarantee certificates for the entire control pipeline. Our solution paves the path for designing fully certifiable autonomy pipelines, by integrating learning-based components, such as perception, with certifiable model-based decision-making through the proposed LCA approach.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Imitation learning methods, one of 13 directions in Offline RL and imitation learning from data. Builds on 35 of its 67 references that are in the map. First posted on arXiv 19 Dec 2025.

Builds on

35 of 67 references.

Closest ancestors · 12

Same direction, newest first

  1. 2022Robust Imitation Learning against Variations in Environment Dynamics19 Jun
  2. 2022TaSIL: Taylor Series Imitation Learning30 May
  3. 2022Imitation Learning by Estimating Expertise of Demonstrators2 Feb
  4. 2021ThriftyDAgger: Budget-Aware Novelty and Risk Gating for Interactive Imitation Learning17 Sep
  5. 2021On the Sample Complexity of Stability Constrained Imitation Learning18 Feb
  6. 2020Imitation Learning with Stability and Safety Guarantees16 Dec
  7. 2019Random Expert Distillation: Imitation Learning via Expert Policy Support Estimation16 May
  8. 2019Imitation Learning from Imperfect Demonstration27 Jan
  9. 2019On the Global Convergence of Imitation Learning: A Case for Linear Quadratic Regulator11 Jan
  10. 2018An Algorithmic Perspective on Imitation Learning16 Nov
  11. 2018HG-DAgger: Interactive Imitation Learning with Human Experts5 Oct
  12. 2018Safe end-to-end imitation learning for model predictive control27 Mar

Other references · 23

  1. 2016Generative Adversarial Imitation Learningcited by 1,576
  2. 2017End-to-end Driving via Conditional Imitation Learningcited by 479
  3. 2017Time-Contrastive Networks: Self-Supervised Learning from Videocited by 453
  4. 2017DART: Noise Injection for Robust Imitation Learningcited by 187
  5. 2017Imitation from Observation: Learning to Imitate Behaviors from Raw Video via Context Translationcited by 167
  6. 2017Third-Person Imitation Learningcited by 103
  7. 2017Robust Imitation of Diverse Behaviorscited by 85
  8. 2016Query-Efficient Imitation Learning for End-to-End Autonomous Drivingcited by 83
  9. 2023Waypoint-Based Imitation Learning for Robotic Manipulationcited by 59
  10. 2018Learning an Approximate Model Predictive Controller with Guaranteescited by 54
  11. 2021Contraction Theory for Nonlinear Stability Analysis and Learning-based Control: A Tutorial Overviewcited by 42
  12. 2024JUICER: Data-Efficient Imitation Learning for Robotic Assemblycited by 36
11 more
  1. 2022Lyapunov Density Models: Constraining Distribution Shift in Learning-Based Controlcited by 28
  2. 2020Probabilistic End-to-End Vehicle Navigation in Complex Dynamic Environments with Multimodal Sensor Fusioncited by 23
  3. 2018Dual Policy Iterationcited by 22
  4. 2017FaSTrack: a Modular Framework for Fast and Guaranteed Safe Motion Planningcited by 21
  5. 2024SAFE-GIL: SAFEty Guided Imitation Learning for Robotic Systemscited by 13
  6. 2020Safe Feedback Motion Planning: A Contraction Theory and L1-Adaptive Control Based Approachcited by 11
  7. 2016Smooth Imitation Learning for Online Sequence Predictioncited by 9
  8. 2021Non-Euclidean Contraction Theory for Robust Nonlinear Stabilitycited by 8
  9. 2024Towards a Theory of Control Architecture: A quantitative framework for layered multi-rate controlcited by 4
  10. 2023StROL: Stabilized and Robust Online Learning from Humanscited by 3
  11. 2025L1-DRAC: Distributionally Robust Adaptive Controlcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Distributionally Robust and Safe Imitation Learningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Balance Equation-based Distributionally Robust Offline Imitation Learning
  2. 2026How to Mitigate the Distribution Shift Problem in Robotics Control: A Robust and Adaptive Approach Based on Offline to Online Imitation Learning
  3. 2022Robust Learning from Observation with Model Misspecification
  4. 2022Robust Imitation of a Few Demonstrations with a Backwards Model
  5. 2024Fusion Dynamical Systems with Machine Learning in Imitation Learning: A Comprehensive Overview
  6. 2025The Pitfalls of Imitation Learning when Actions are Continuous
  7. 2023Hierarchical Imitation Learning for Stochastic Environments
  8. 2022Imitating, Fast and Slow: Robust learning from demonstrations via decision-time planning