# Distributionally Robust and Safe Imitation Learning

arXiv: https://arxiv.org/abs/2607.13436 · HTML: https://mlsanity.com/paper/2607.13436/

## 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.

## Placed in

- Offline RL and imitation learning from data / [Imitation learning methods](https://mlsanity.com/offlinerl/imitation-learning-methods/)

## Builds on (most cited first, 14 of 14)

- [Generative Adversarial Imitation Learning](https://mlsanity.com/paper/1606.03476/) (2016)
- [Certifying Some Distributional Robustness with Principled Adversarial Training](https://mlsanity.com/paper/1710.10571/) (2017)
- [A Survey of Inverse Reinforcement Learning: Challenges, Methods and Progress](https://mlsanity.com/paper/1806.06877/) (2018)
- [DART: Noise Injection for Robust Imitation Learning](https://mlsanity.com/paper/1703.09327/) (2017)
- [A Survey of Imitation Learning: Algorithms, Recent Developments, and Challenges](https://mlsanity.com/paper/2309.02473/) (2023)
- [Recent Advances in Imitation Learning from Observation](https://mlsanity.com/paper/1905.13566/) (2019)
- [Data Quality in Imitation Learning](https://mlsanity.com/paper/2306.02437/) (2023)
- [Robust Imitation Learning against Variations in Environment Dynamics](https://mlsanity.com/paper/2206.09314/) (2022)
- [TaSIL: Taylor Series Imitation Learning](https://mlsanity.com/paper/2205.14812/) (2022)
- [A Mathematical Theory of Co-Design](https://mlsanity.com/paper/1512.08055/) (2015)
- [Efficient Deep Learning of Robust Policies from MPC using Imitation and Tube-Guided Data Augmentation](https://mlsanity.com/paper/2306.00286/) (2023)
- [L1-DRAC: Distributionally Robust Adaptive Control](https://mlsanity.com/paper/2509.04619/) (2025)
- [Wasserstein Distributionally Robust Adaptive Covariance Steering](https://mlsanity.com/paper/2509.04593/) (2025)
- [Distributionally Robust Imitation Learning: Layered Control Architecture for Certifiable Autonomy](https://mlsanity.com/paper/2512.17899/) (2025)

## 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.