mlsanityData to 7 Oct 2026

ASkDAgger: Active Skill-level Data Aggregation for Interactive Imitation Learning

arXiv 2508.05310 ↗First posted 7 Aug 2025cs.LG cs.AI cs.HCcited by 0

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

Abstract (arXiv)

Human teaching effort is a significant bottleneck for the broader applicability of interactive imitation learning. To reduce the number of required queries, existing methods employ active learning to query the human teacher only in uncertain, risky, or novel situations. However, during these queries, the novice's planned actions are not utilized despite containing valuable information, such as the novice's capabilities, as well as corresponding uncertainty levels. To this end, we allow the novice to say: "I plan to do this, but I am uncertain." We introduce the Active Skill-level Data Aggregation (ASkDAgger) framework, which leverages teacher feedback on the novice plan in three key ways: (1) S-Aware Gating (SAG): Adjusts the gating threshold to track sensitivity, specificity, or a minimum success rate; (2) Foresight Interactive Experience Replay (FIER), which recasts valid and relabeled novice action plans into demonstrations; and (3) Prioritized Interactive Experience Replay (PIER), which prioritizes replay based on uncertainty, novice success, and demonstration age. Together, these components balance query frequency with failure incidence, reduce the number of required demonstration annotations, improve generalization, and speed up adaptation to changing domains. We validate the effectiveness of ASkDAgger through language-conditioned manipulation tasks in both simulation and real-world environments. Code, data, and videos are available at https://askdagger.github.io.

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 36 of its 53 references that are in the map. First posted on arXiv 7 Aug 2025.

Builds on

36 of 53 references.

Closest ancestors · 7

Same direction, newest first

  1. 2023RLIF: Interactive Imitation Learning as Reinforcement Learning21 Nov
  2. 2023IIFL: Implicit Interactive Fleet Learning from Heterogeneous Human Supervisors27 Jun
  3. 2023Asking for Help: Failure Prediction in Behavioral Cloning through Value Approximation8 Feb
  4. 2022Interactive Imitation Learning in Robotics: A Survey31 Oct
  5. 2021ThriftyDAgger: Budget-Aware Novelty and Risk Gating for Interactive Imitation Learning17 Sep
  6. 2019Uncertainty-Aware Data Aggregation for Deep Imitation Learning7 May
  7. 2018HG-DAgger: Interactive Imitation Learning with Human Experts5 Oct

Other references · 29

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  3. 2022RT-1: Robotics Transformer for Real-World Control at Scalecited by 2,007
  4. 2024Octo: An Open-Source Generalist Robot Policycited by 1,427
  5. 2017Hindsight Experience Replaycited by 1,096
  6. 2015Prioritized Experience Replaycited by 1,070
  7. 2022A Generalist Agentcited by 802
  8. 2021CLIPort: What and Where Pathways for Robotic Manipulationcited by 617
  9. 2022Google Scanned Objects: A High-Quality Dataset of 3D Scanned Household Itemscited by 601
  10. 2022BC-Z: Zero-Shot Task Generalization with Robotic Imitation Learningcited by 517
  11. 2020Transporter Networks: Rearranging the Visual World for Robotic Manipulationcited by 342
  12. 2023Robots That Ask For Help: Uncertainty Alignment for Large Language Model Plannerscited by 298
17 more
  1. 2023A Survey of Reinforcement Learning from Human Feedbackcited by 259
  2. 2021Where2Act: From Pixels to Actions for Articulated 3D Objectscited by 179
  3. 2019Gradio: Hassle-Free Sharing and Testing of ML Models in the Wildcited by 176
  4. 2021Error-Aware Imitation Learning from Teleoperation Data for Mobile Manipulationcited by 59
  5. 2021AdaAfford: Learning to Adapt Manipulation Affordance for 3D Articulated Objects via Few-shot Interactionscited by 56
  6. 2022End-to-End Affordance Learning for Robotic Manipulationcited by 54
  7. 2023Model-Based Runtime Monitoring with Interactive Imitation Learningcited by 37
  8. 2023Where2Explore: Few-shot Affordance Learning for Unseen Novel Categories of Articulated Objectscited by 33
  9. 2022Fleet-DAgger: Interactive Robot Fleet Learning with Scalable Human Supervisioncited by 29
  10. 2024Diff-DAgger: Uncertainty Estimation with Diffusion Policy for Robotic Manipulationcited by 29
  11. 2020LaND: Learning to Navigate from Disengagementscited by 24
  12. 2021Information Directed Reward Learning for Reinforcement Learningcited by 24
  13. 2017DropoutDAgger: A Bayesian Approach to Safe Imitation Learningcited by 14
  14. 2023Embodied Active Learning of Relational State Abstractions for Bilevel Planningcited by 8
  15. 2024Information-driven Affordance Discovery for Efficient Robotic Manipulationcited by 4
  16. 2021Back to Reality for Imitation Learningcited by 3
  17. 2022PARTNR: Pick and place Ambiguity Resolving by Trustworthy iNteractive leaRningcited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2020Active Imitation Learning from Multiple Non-Deterministic Teachers: Formulation, Challenges, and Algorithms
  2. 2024VITAL: Interactive Few-Shot Imitation Learning via Visual Human-in-the-Loop Corrections
  3. 2023How To Guide Your Learner: Imitation Learning with Active Adaptive Expert Involvement
  4. 2022Learning and Retrieval from Prior Data for Skill-based Imitation Learning
  5. 2023MimicPlay: Long-Horizon Imitation Learning by Watching Human Play
  6. 2023Agnostic Interactive Imitation Learning: New Theory and Practical Algorithms
  7. 2023Information Maximizing Curriculum: A Curriculum-Based Approach for Imitating Diverse Skills
  8. 2021Imitation Learning: Progress, Taxonomies and Challenges