结合神经与符号方法，利用人眼注视数据提升模仿学习效率与泛化能力
Neurosymbolic Imitation Learning with Human Guidance: A Privileged Information Approach
- 融合神经网络与符号系统，兼顾高维输入处理与泛化能力
- 训练时利用人类注视数据作为特权信息，显著减少所需样本数
- 适合需要高效学习且依赖人类先验知识的复杂任务场景
模仿学习广泛应用于复杂环境中的行为学习。纯神经方法虽能有效处理高维数据，但需大量样本且易过拟合；纯符号方法虽泛化能力强，却难以处理高维输入。本文提出一种神经符号方法，兼具高维数据处理与良好泛化能力。其关键优势在于可有效利用仅在训练阶段可用的额外特权信息（本研究中为眼球注视数据）。实证评估表明，所提方法在有效性、效率和泛化能力方面均表现优异。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。