Deduction with Induction: Combining Knowledge Discovery and Reasoning for Interpretable Deep Reinforcement Learning

Haodi Zhang; Xiangyu Zeng; Junyang Chen; Yuanfeng Song; Rui Mao; Fangzhen Lin

IJCAI 20250 citations

Deduction with Induction: Combining Knowledge Discovery and Reasoning for Interpretable Deep Reinforcement Learning

Haodi Zhang, Xiangyu Zeng, Junyang Chen, Yuanfeng Song, Rui Mao, Fangzhen Lin

Abstract

Deep reinforcement learning (DRL) has achieved remarkable success in dynamic decision-making tasks. However, its inherent opacity and cold start problem hinder transparency and training efficiency. To address these challenges, we propose HRL-ID, a neural-symbolic framework that combines automated rule discovery with logical reasoning within a hierarchical DRL structure. HRL-ID dynamically extracts first-order logic rules from environmental interactions, iteratively refines them through success-based updates, and leverages these rules to guide action execution during training. Extensive experiments on Atari benchmarks demonstrate that HRL-ID outperforms state-of-the-art methods in training efficiency and interpretability, achieving higher reward rates and successful knowledge transfer between domains.

BibTeX

@inproceedings{ijcai2025_deductionwithind,
  title = {Deduction with Induction: Combining Knowledge Discovery and Reasoning for Interpretable Deep Reinforcement Learning},
  author = {Haodi Zhang and Xiangyu Zeng and Junyang Chen and Yuanfeng Song and Rui Mao and Fangzhen Lin},
  booktitle = {IJCAI 2025},
  year = {2025}
}