{"type":"ScholarlyArticle","title":"Deduction with Induction: Combining Knowledge Discovery and Reasoning for Interpretable Deep Reinforcement Learning","authors":[{"name":"Haodi Zhang","slug":"haodi-zhang","given":"Haodi","family":"Zhang","affiliation":""},{"name":"Xiangyu Zeng","slug":"xiangyu-zeng","given":"Xiangyu","family":"Zeng","affiliation":""},{"name":"Junyang Chen","slug":"junyang-chen","given":"Junyang","family":"Chen","affiliation":""},{"name":"Yuanfeng Song","slug":"yuanfeng-song","given":"Yuanfeng","family":"Song","affiliation":""},{"name":"Rui Mao","slug":"rui-mao","given":"Rui","family":"Mao","affiliation":""},{"name":"Fangzhen Lin","slug":"fangzhen-lin","given":"Fangzhen","family":"Lin","affiliation":""}],"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.","doi":"10.24963/ijcai.2025/777","url":"https://ijcai.org/proceedings/2025/777","pdf":"https://ijcai.org/proceedings/2025/0777.pdf","markdown":"https://ijcai.org/proceedings/2025/777.md","bibtex":"https://ijcai.org/proceedings/2025/bibtex/777","volume":{"slug":"2025","title":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2025","url":"https://ijcai.org/proceedings/2025/","year":2025,"location":"Montreal, Canada","dates":"16-22 August 2025","editors":"James Kwok","isbn":"978-1-956792-06-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2025"},"section":"Machine Learning","track":"Main Track","number":777,"pages":{"first":6984,"last":6992},"keywords":["Machine Learning: ML: Reinforcement learning","Machine Learning: ML: Knowledge-aided learning","Machine Learning: ML: Neuro-symbolic methods/Abductive Learning"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}