STAND: Self-Aware Precondition Induction for Interactive Task Learning
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914305137442816 |
|---|---|
| author | Weitekamp, Daniel Smith, Glen Koedinger, Kenneth MacLellan, Christopher |
| author_facet | Weitekamp, Daniel Smith, Glen Koedinger, Kenneth MacLellan, Christopher |
| contents | In interactive task learning (ITL), AI agents learn new capabilities from limited human instruction provided during task execution. STAND is a new method of data-efficient rule precondition induction specifically designed for these human-in-the-loop training scenarios. A key feature of STAND is its self-awareness of its own learning -- it can provide accurate metrics of training progress back to users. STAND beats popular methods like XGBoost, decision trees, random forests, and version spaces at small-data precondition induction tasks, and is highly accurate at estimating when its performance improves on holdout examples. In our evaluations, we find that STAND shows more monotonic improvement than other models with low rates of error recurrence. These features of STAND support a more consistent training experience, enabling human instructors to estimate when they are finished training and providing active-learning support by identifying trouble spots where more training is required. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_07653 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | STAND: Self-Aware Precondition Induction for Interactive Task Learning Weitekamp, Daniel Smith, Glen Koedinger, Kenneth MacLellan, Christopher Machine Learning In interactive task learning (ITL), AI agents learn new capabilities from limited human instruction provided during task execution. STAND is a new method of data-efficient rule precondition induction specifically designed for these human-in-the-loop training scenarios. A key feature of STAND is its self-awareness of its own learning -- it can provide accurate metrics of training progress back to users. STAND beats popular methods like XGBoost, decision trees, random forests, and version spaces at small-data precondition induction tasks, and is highly accurate at estimating when its performance improves on holdout examples. In our evaluations, we find that STAND shows more monotonic improvement than other models with low rates of error recurrence. These features of STAND support a more consistent training experience, enabling human instructors to estimate when they are finished training and providing active-learning support by identifying trouble spots where more training is required. |
| title | STAND: Self-Aware Precondition Induction for Interactive Task Learning |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2409.07653 |