Abductive Learning for Neuro-Symbolic Grounded Imitation

Jie-Jing Shao1, Hao-Ran Hao1, Xiao-Wen Yang1, Yu-Feng Li1,
1Nanjing University, LAMDA Group
KDD 2025
arXiv Paper Code

Our framework, ABductive Imitation Learning (ABIL), achieves neuro-symbolic grounding of imitation in complex scenes while showing state-of-the-art results in data efficiency, generalization, and zero-shot transfer.

Abstract

Recent learning-to-imitation methods have shown promising results in planning via imitating within the observation-action space. However, their ability in open environments remains constrained, particularly in long-horizon tasks. In contrast, traditional symbolic planning excels in long-horizon tasks through logical reasoning over human-defined symbolic spaces but struggles to handle observations beyond symbolic states, such as high-dimensional visual inputs encountered in real-world scenarios. In this work, we draw inspiration from abductive learning and introduce a novel framework ABductive Imitation Learning (ABIL) that integrates the benefits of data-driven learning and symbolic-based reasoning, enabling long-horizon planning. Specifically, we employ abductive reasoning to understand the demonstrations in symbolic space and design the principles of sequential consistency to resolve the conflicts between perception and reasoning. ABIL generates predicate candidates to facilitate the perception from raw observations to symbolic space without laborious predicate annotations, providing a groundwork for symbolic planning. With the symbolic understanding, we further develop a policy ensemble whose base policies are built with different logical objectives and managed through symbolic reasoning. Experiments show that our proposal successfully understands the observations with the task-relevant symbolics to assist the imitation learning. Importantly, ABIL demonstrates significantly improved data efficiency and generalization across various long-horizon tasks, highlighting it as a promising solution for long-horizon planning.

BibTeX

@misc{shao2024learninglonghorizonplanningneurosymbolic,
      title={Learning for Long-Horizon Planning via Neuro-Symbolic Abductive Imitation}, 
      author={Jie-Jing Shao and Hao-Ran Hao and Xiao-Wen Yang and Yu-Feng Li},
      year={2024},
      eprint={2411.18201},
      archivePrefix={arXiv},
      primaryClass={cs.LG},
      url={https://arxiv.org/abs/2411.18201}, 
}
}