mlsanityData to 7 Oct 2026

Neurosymbolic Imitation Learning with Human Guidance: A Privileged Information Approach

arXiv 2605.07166 ↗First posted 8 May 2026cs.LGcited by 0

On the map: Offline RL and imitation learning from data → Robot manipulation imitation learning

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Robot manipulation imitation learning, one of 13 directions in Offline RL and imitation learning from data. Builds on 19 of its 49 references that are in the map. First posted on arXiv 8 May 2026.

Builds on

19 of 49 references.

Closest ancestors · 2

Same direction, newest first

  1. 2025GABRIL: Gaze-Based Regularization for Mitigating Causal Confusion in Imitation Learning25 Jul
  2. 2021Imitation Learning with Human Eye Gaze via Multi-Objective Prediction25 Feb

Other references · 17

  1. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  2. 2018An Algorithmic Perspective on Imitation Learningcited by 455
  3. 2015Unifying distillation and privileged informationcited by 218
  4. 2017Learning Explanatory Rules from Noisy Datacited by 210
  5. 2022Predicate Invention for Bilevel Planningcited by 49
  6. 2018AGIL: Learning Attention from Human for Visuomotor Taskscited by 32
  7. 2018Learning with privileged information via adversarial discriminative modality distillationcited by 30
  8. 2018Deep Learning under Privileged Information Using Heteroscedastic Dropoutcited by 26
  9. 2019Periphery-Fovea Multi-Resolution Driving Model guided by Human Attentioncited by 19
  10. 2021Gaze-based dual resolution deep imitation learning for high-precision dexterous robot manipulationcited by 16
  11. 2021Neuro-Symbolic Forward Reasoningcited by 16
  12. 2022Toward Understanding Privileged Features Distillation in Learning-to-Rankcited by 16
5 more
  1. 2022Transfer and Marginalize: Explaining Away Label Noise with Privileged Informationcited by 15
  2. 2024ViSaRL: Visual Reinforcement Learning Guided by Human Saliencycited by 12
  3. 2019Gaze Training by Modulated Dropout Improves Imitation Learningcited by 10
  4. 2014Mind the Nuisance: Gaussian Process Classification using Privileged Noisecited by 7
  5. 2022Visual Attention Prediction Improves Performance of Autonomous Drone Racing Agentscited by 6

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2022Learning and Retrieval from Prior Data for Skill-based Imitation Learning
  2. 2025Neuro-Symbolic Imitation Learning: Discovering Symbolic Abstractions for Skill Learning
  3. 2023Behavior Retrieval: Few-Shot Imitation Learning by Querying Unlabeled Datasets
  4. 2024Towards Diverse Behaviors: A Benchmark for Imitation Learning with Human Demonstrations
  5. 2025Generalization Capability for Imitation Learning
  6. 2025NIL: No-data Imitation Learning by Leveraging Pre-trained Video Diffusion Models
  7. 2025Few-Shot Neuro-Symbolic Imitation Learning for Long-Horizon Planning and Acting
  8. 2025Imitation Learning in the Deep Learning Era: A Novel Taxonomy and Recent Advances