Neurosymbolic Imitation Learning with Human Guidance: A Privileged Information Approach
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915991532863488 |
|---|---|
| author | Prabhakar, Nikhilesh Balaji, Varun Karanam, Athresh Kersting, Kristian Natarajan, Sriraam |
| author_facet | Prabhakar, Nikhilesh Balaji, Varun Karanam, Athresh Kersting, Kristian Natarajan, Sriraam |
| contents | Imitation learning is widely used for learning to act in complex environments. While pure neural-based methods handle high dimensional data effectively, they suffer from the requirement of large number of samples and are prone to overfitting. Pure symbolic approaches, while generalize well, do not handle high-dimensional data effectively. We propose a neurosymbolic approach that achieves the best of both worlds, i.e, handling high-dimensional data while achieving generalization. The key advantage of our approach is that it can effectively exploit additional privileged information that is available only during training (in our case, gaze data). Our empirical evaluations demonstrate the effectiveness, efficiency and the generalization capability of our proposed approach. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_07166 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Neurosymbolic Imitation Learning with Human Guidance: A Privileged Information Approach Prabhakar, Nikhilesh Balaji, Varun Karanam, Athresh Kersting, Kristian Natarajan, Sriraam Machine Learning Imitation learning is widely used for learning to act in complex environments. While pure neural-based methods handle high dimensional data effectively, they suffer from the requirement of large number of samples and are prone to overfitting. Pure symbolic approaches, while generalize well, do not handle high-dimensional data effectively. We propose a neurosymbolic approach that achieves the best of both worlds, i.e, handling high-dimensional data while achieving generalization. The key advantage of our approach is that it can effectively exploit additional privileged information that is available only during training (in our case, gaze data). Our empirical evaluations demonstrate the effectiveness, efficiency and the generalization capability of our proposed approach. |
| title | Neurosymbolic Imitation Learning with Human Guidance: A Privileged Information Approach |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2605.07166 |