mlsanityData to 7 Oct 2026

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

arXiv 2510.00906 ↗First posted 1 Oct 2025eess.SY cs.AI cs.LGcited by 0

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

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.

Key facts. No citing papers in the map yet (data through 7 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.

Builds on

17 of 26 references.

Closest ancestors · 4

Same direction, newest first

  1. 2018HG-DAgger: Interactive Imitation Learning with Human Experts5 Oct
  2. 2018Risk-Sensitive Generative Adversarial Imitation Learning13 Aug
  3. 2018EnsembleDAgger: A Bayesian Approach to Safe Imitation Learning22 Jul
  4. 2018Fast Policy Learning through Imitation and Reinforcement26 May

Other references · 13

  1. 2017One-Shot Imitation Learningcited by 232
  2. 2017DART: Noise Injection for Robust Imitation Learningcited by 187
  3. 2017Hamilton-Jacobi Reachability: A Brief Overview and Recent Advancescited by 186
  4. 2017Interactive Learning from Policy-Dependent Human Feedbackcited by 155
  5. 2021SafetyNet: Safe planning for real-world self-driving vehicles using machine-learned policiescited by 68
  6. 2021LazyDAgger: Reducing Context Switching in Interactive Imitation Learningcited by 50
  7. 2024RACER: Rich Language-Guided Failure Recovery Policies for Imitation Learningcited by 46
  8. 2016PLATO: Policy Learning using Adaptive Trajectory Optimizationcited by 23
  9. 2020Lagrangian Reachtubes: The Next Generationcited by 10
  10. 2020Safety Verification of Unknown Dynamical Systems via Gaussian Process Regressioncited by 9
  11. 2023Data-Driven Reachability Analysis of Stochastic Dynamical Systems with Conformal Inferencecited by 9
  12. 2023Real-Time Recurrent Reinforcement Learningcited by 6
1 more
  1. 2017Underapproximation of Reach-Avoid Sets for Discrete-Time Stochastic Systems via Lagrangian Methodscited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025The Pitfalls of Imitation Learning when Actions are Continuous
  2. 2023Selective Sampling and Imitation Learning via Online Regression
  3. 2026Behavior Cloning is Not All You Need: The Optimality of On-Policy Distillation for Noisy Expert Feedback
  4. 2022Imitation Learning by Estimating Expertise of Demonstrators
  5. 2024Efficient Active Imitation Learning with Random Network Distillation
  6. 2022Minimax Optimal Online Imitation Learning via Replay Estimation
  7. 2022Deconfounding Imitation Learning with Variational Inference
  8. 2023Agnostic Interactive Imitation Learning: New Theory and Practical Algorithms