---
title: "Deduction with Induction: Combining Knowledge Discovery and Reasoning for Interpretable Deep Reinforcement Learning"
authors:
  - "Haodi Zhang"
  - "Xiangyu Zeng"
  - "Junyang Chen"
  - "Yuanfeng Song"
  - "Rui Mao"
  - "Fangzhen Lin"
doi: "10.24963/ijcai.2025/777"
url: "https://ijcai.org/proceedings/2025/777"
pdf: "https://ijcai.org/proceedings/2025/0777.pdf"
venue: "Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence"
year: 2025
pages: "6984-6992"
track: "Main Track"
keywords:
  - "Machine Learning: ML: Reinforcement learning"
  - "Machine Learning: ML: Knowledge-aided learning"
  - "Machine Learning: ML: Neuro-symbolic methods/Abductive Learning"
---

# 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

*Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence*, pages 6984-6992. DOI: [10.24963/ijcai.2025/777](https://doi.org/10.24963/ijcai.2025/777)

## 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.