{"id":"https://openalex.org/W4414359595","doi":"https://doi.org/10.24963/ijcai.2025/777","title":"Deduction with Induction: Combining Knowledge Discovery and Reasoning for Interpretable Deep Reinforcement Learning","display_name":"Deduction with Induction: Combining Knowledge Discovery and Reasoning for Interpretable Deep Reinforcement Learning","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414359595","doi":"https://doi.org/10.24963/ijcai.2025/777"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/777","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/777","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5059498267","display_name":"Haodi Zhang","orcid":"https://orcid.org/0000-0001-8470-7246"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Haodi Zhang","raw_affiliation_strings":["Shenzhen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen University","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100308797","display_name":"X. Zeng","orcid":"https://orcid.org/0000-0001-9701-3964"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangyu Zeng","raw_affiliation_strings":["Shenzhen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen University","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045191293","display_name":"Junyang Chen","orcid":"https://orcid.org/0000-0002-1139-8654"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junyang Chen","raw_affiliation_strings":["Shenzhen Univeristy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Univeristy","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077688051","display_name":"Yuanfeng Song","orcid":"https://orcid.org/0000-0003-2221-9807"},"institutions":[{"id":"https://openalex.org/I4210145740","display_name":"West Bengal Electronics Industry Development Corporation Limited (India)","ror":"https://ror.org/03y350s17","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210145740"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Yuanfeng Song","raw_affiliation_strings":["WeBank"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"WeBank","institution_ids":["https://openalex.org/I4210145740"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101724957","display_name":"Rui Mao","orcid":"https://orcid.org/0000-0002-3645-5520"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Mao","raw_affiliation_strings":["Shenzhen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen University","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102011179","display_name":"Fangzhen Lin","orcid":"https://orcid.org/0000-0002-3141-8675"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Fangzhen Lin","raw_affiliation_strings":["Hong Kong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5059498267"],"corresponding_institution_ids":["https://openalex.org/I180726961"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.12191936,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6984","last_page":"6992"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.8101000189781189,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.8101000189781189,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7386999726295471},{"id":"https://openalex.org/keywords/transparency","display_name":"Transparency (behavior)","score":0.4830000102519989},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.42289999127388},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.3896999955177307},{"id":"https://openalex.org/keywords/knowledge-extraction","display_name":"Knowledge extraction","score":0.35760000348091125},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.3456999957561493},{"id":"https://openalex.org/keywords/knowledge-representation-and-reasoning","display_name":"Knowledge representation and reasoning","score":0.32589998841285706}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7555000185966492},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7386999726295471},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7077000141143799},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5159000158309937},{"id":"https://openalex.org/C2780233690","wikidata":"https://www.wikidata.org/wiki/Q535347","display_name":"Transparency (behavior)","level":2,"score":0.4830000102519989},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.42289999127388},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3896999955177307},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.35760000348091125},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.3456999957561493},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.32589998841285706},{"id":"https://openalex.org/C2777220311","wikidata":"https://www.wikidata.org/wiki/Q6423340","display_name":"Knowledge acquisition","level":2,"score":0.3127000033855438},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3034999966621399},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.2994000017642975},{"id":"https://openalex.org/C114073186","wikidata":"https://www.wikidata.org/wiki/Q2631895","display_name":"Automated planning and scheduling","level":2,"score":0.2736999988555908},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.2736000120639801},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2581999897956848},{"id":"https://openalex.org/C86827895","wikidata":"https://www.wikidata.org/wiki/Q7098582","display_name":"Opportunistic reasoning","level":4,"score":0.25119999051094055}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.24963/ijcai.2025/777","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/777","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-169113","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-169113","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Deep":[0],"reinforcement":[1],"learning":[2],"(DRL)":[3],"has":[4],"achieved":[5],"remarkable":[6],"success":[7],"in":[8,84],"dynamic":[9],"decision-making":[10],"tasks.":[11],"However,":[12],"its":[13],"inherent":[14],"opacity":[15],"and":[16,22,63,87,93],"cold":[17],"start":[18],"problem":[19],"hinder":[20],"transparency":[21],"training":[23,85],"efficiency.":[24],"To":[25],"address":[26],"these":[27,65],"challenges,":[28],"we":[29],"propose":[30],"HRL-ID,":[31],"a":[32,44],"neural-symbolic":[33],"framework":[34],"that":[35,79],"combines":[36],"automated":[37],"rule":[38],"discovery":[39],"with":[40],"logical":[41],"reasoning":[42],"within":[43],"hierarchical":[45],"DRL":[46],"structure.":[47],"HRL-ID":[48,80],"dynamically":[49],"extracts":[50],"first-order":[51],"logic":[52],"rules":[53,66],"from":[54],"environmental":[55],"interactions,":[56],"iteratively":[57],"refines":[58],"them":[59],"through":[60],"success-based":[61],"updates,":[62],"leverages":[64],"to":[67],"guide":[68],"action":[69],"execution":[70],"during":[71],"training.":[72],"Extensive":[73],"experiments":[74],"on":[75],"Atari":[76],"benchmarks":[77],"demonstrate":[78],"outperforms":[81],"state-of-the-art":[82],"methods":[83],"efficiency":[86],"interpretability,":[88],"achieving":[89],"higher":[90],"reward":[91],"rates":[92],"successful":[94],"knowledge":[95],"transfer":[96],"between":[97],"domains.":[98]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}