ASkDAgger: Active Skill-level Data Aggregation for Interactive Imitation Learning
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908481083146240 |
|---|---|
| author | Luijkx, Jelle Ajanović, Zlatan Ferranti, Laura Kober, Jens |
| author_facet | Luijkx, Jelle Ajanović, Zlatan Ferranti, Laura Kober, Jens |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_05310 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | ASkDAgger: Active Skill-level Data Aggregation for Interactive Imitation Learning Luijkx, Jelle Ajanović, Zlatan Ferranti, Laura Kober, Jens Machine Learning Artificial Intelligence Human-Computer Interaction Robotics 68T05 I.2.6; I.2.8; I.2.9 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. |
| title | ASkDAgger: Active Skill-level Data Aggregation for Interactive Imitation Learning |
| topic | Machine Learning Artificial Intelligence Human-Computer Interaction Robotics 68T05 I.2.6; I.2.8; I.2.9 |
| url | https://arxiv.org/abs/2508.05310 |