# TubeDAgger: Reducing the Number of Expert Interventions with Stochastic Reach-Tubes

arXiv: https://arxiv.org/abs/2510.00906 · HTML: https://mlsanity.com/paper/2510.00906/

## 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 17 of its 26 references that are in the map.
- First posted on arXiv 1 Oct 2025.

## Placed in

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

## Builds on (most cited first, 17 of 17)

- [HG-DAgger: Interactive Imitation Learning with Human Experts](https://mlsanity.com/paper/1810.02890/) (2018)
- [One-Shot Imitation Learning](https://mlsanity.com/paper/1703.07326/) (2017)
- [Hamilton-Jacobi Reachability: A Brief Overview and Recent Advances](https://mlsanity.com/paper/1709.07523/) (2017)
- [DART: Noise Injection for Robust Imitation Learning](https://mlsanity.com/paper/1703.09327/) (2017)
- [Interactive Learning from Policy-Dependent Human Feedback](https://mlsanity.com/paper/1701.06049/) (2017)
- [EnsembleDAgger: A Bayesian Approach to Safe Imitation Learning](https://mlsanity.com/paper/1807.08364/) (2018)
- [SafetyNet: Safe planning for real-world self-driving vehicles using machine-learned policies](https://mlsanity.com/paper/2109.13602/) (2021)
- [LazyDAgger: Reducing Context Switching in Interactive Imitation Learning](https://mlsanity.com/paper/2104.00053/) (2021)
- [RACER: Rich Language-Guided Failure Recovery Policies for Imitation Learning](https://mlsanity.com/paper/2409.14674/) (2024)
- [Fast Policy Learning through Imitation and Reinforcement](https://mlsanity.com/paper/1805.10413/) (2018)
- [PLATO: Policy Learning using Adaptive Trajectory Optimization](https://mlsanity.com/paper/1603.00622/) (2016)
- [Risk-Sensitive Generative Adversarial Imitation Learning](https://mlsanity.com/paper/1808.04468/) (2018)
- [Lagrangian Reachtubes: The Next Generation](https://mlsanity.com/paper/2012.07458/) (2020)
- [Safety Verification of Unknown Dynamical Systems via Gaussian Process Regression](https://mlsanity.com/paper/2004.01821/) (2020)
- [Data-Driven Reachability Analysis of Stochastic Dynamical Systems with Conformal Inference](https://mlsanity.com/paper/2309.09187/) (2023)
- [Real-Time Recurrent Reinforcement Learning](https://mlsanity.com/paper/2311.04830/) (2023)
- [Underapproximation of Reach-Avoid Sets for Discrete-Time Stochastic Systems via Lagrangian Methods](https://mlsanity.com/paper/1704.03555/) (2017)

## Abstract (arXiv)

Interactive Imitation Learning deals with training a novice policy from expert demonstrations in an online fashion. The established DAgger algorithm trains a robust novice policy by alternating between interacting with the environment and retraining of the network. Many variants thereof exist, that differ in the method of discerning whether to allow the novice to act or return control to the expert. We propose the use of stochastic reachtubes - common in verification of dynamical systems - as a novel method for estimating the necessity of expert intervention. Our approach does not require fine-tuning of decision thresholds per environment and effectively reduces the number of expert interventions, especially when compared with related approaches that make use of a doubt classification model.