mlsanityData to 14 Oct 2026

Distributionally Robust and Safe Imitation Learning

arXiv 2607.13436 ↗First posted 15 Jul 2026cs.LG cs.SY eess.SYcited by 0

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

Abstract (arXiv)

Imitation learning (IL) has achieved remarkable success in complex decision-making tasks. However, its performance is highly sensitive to distribution shifts, which can pose significant safety risks. We propose a distributionally robust and safe IL framework that explicitly addresses both policy-induced and uncertainty-induced distribution shifts. Our approach develops a unified framework leveraging Taylor Series Imitation Learning (TaSIL) to mitigate policy-induced shifts and distributionally robust adaptive control to handle uncertainty-induced shifts. This architecture enables the formulation of an IL problem that optimizes performance under distributional uncertainty while systematically accounting for safety constraints. We demonstrate the effectiveness of the proposed approach on an unmanned aerial vehicle (UAV) case study where the UAV performs a task in an uncertain environment while avoiding unsafe regions.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Imitation learning methods, one of 13 directions in Offline RL and imitation learning from data. Builds on 14 of its 20 references that are in the map. First posted on arXiv 15 Jul 2026.

Builds on

14 of 20 references.

Closest ancestors · 6

Same direction, newest first

  1. 2025Distributionally Robust Imitation Learning: Layered Control Architecture for Certifiable Autonomy19 Dec
  2. 2023A Survey of Imitation Learning: Algorithms, Recent Developments, and Challenges5 Sep
  3. 2023Efficient Deep Learning of Robust Policies from MPC using Imitation and Tube-Guided Data Augmentation1 Jun
  4. 2022Robust Imitation Learning against Variations in Environment Dynamics19 Jun
  5. 2022TaSIL: Taylor Series Imitation Learning30 May
  6. 2019Recent Advances in Imitation Learning from Observation30 May

Other references · 8

  1. 2016Generative Adversarial Imitation Learningcited by 1,597
  2. 2017Certifying Some Distributional Robustness with Principled Adversarial Trainingcited by 337
  3. 2018A Survey of Inverse Reinforcement Learning: Challenges, Methods and Progresscited by 298
  4. 2017DART: Noise Injection for Robust Imitation Learningcited by 191
  5. 2023Data Quality in Imitation Learningcited by 75
  6. 2015A Mathematical Theory of Co-Designcited by 10
  7. 2025L1-DRAC: Distributionally Robust Adaptive Controlcited by 2
  8. 2025Wasserstein Distributionally Robust Adaptive Covariance Steeringcited by 1

Built on by

Not cited yet.

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. 2025RISE: Robust Imitation through Stochastic Encoding
  4. 2022Robust Learning from Observation with Model Misspecification
  5. 2026TAIL-Safe: Task-Agnostic Safety Monitoring for Imitation Learning Policies
  6. 2021Bayesian Disturbance Injection: Robust Imitation Learning of Flexible Policies
  7. 2025DIAL: Distribution-Informed Adaptive Learning of Multi-Task Constraints for Safety-Critical Systems
  8. 2024SAFE-GIL: SAFEty Guided Imitation Learning for Robotic Systems