Publikation
Neurosymbolic Imitation Learning with Human Guidance: A Privileged Information Approach
Nikhilesh Prabhakar; Varun Balaji; Athresh Karanam; Kristian Kersting; Sriraam Natarajan
In: Computing Research Repository eprint Journal (CoRR), Vol. abs/2605.07166, Pages 1-24, arXiv, 2026.
Zusammenfassung
Imitation learning is widely used for learning to act in com-
plex environments. While pure neural-based methods handle high dimen-
sional 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 pro-
pose 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, ef-
ficiency and the generalization capability of our proposed approach.