{"id":"https://openalex.org/W4414360249","doi":"https://doi.org/10.24963/ijcai.2025/725","title":"From End-to-end to Step-by-step: Learning to Abstract via Abductive Reinforcement Learning","display_name":"From End-to-end to Step-by-step: Learning to Abstract via Abductive Reinforcement Learning","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414360249","doi":"https://doi.org/10.24963/ijcai.2025/725"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/725","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/725","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/A5101489985","display_name":"Zilong Wang","orcid":"https://orcid.org/0009-0006-8979-0572"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]},{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zilong Wang","raw_affiliation_strings":["National Key Laboratory for Novel Software Technology, Nanjing University","School of Intelligence Science and Technology, Nanjing University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology, Nanjing University","institution_ids":["https://openalex.org/I881766915"]},{"raw_affiliation_string":"School of Intelligence Science and Technology, Nanjing University","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000205810","display_name":"Jiongda Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiongda Wang","raw_affiliation_strings":["School of Intelligence Science and Technology, Nanjing University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Intelligence Science and Technology, Nanjing University","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082292467","display_name":"Xiaoyong Chen","orcid":"https://orcid.org/0000-0003-4963-1666"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyong Chen","raw_affiliation_strings":["School of Intelligence Science and Technology, Nanjing University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Intelligence Science and Technology, Nanjing University","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100377144","display_name":"Meng Wang","orcid":"https://orcid.org/0000-0002-2857-2022"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meng Wang","raw_affiliation_strings":["School of Intelligence Science and Technology, Nanjing University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Intelligence Science and Technology, Nanjing University","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014222203","display_name":"Ming Ma","orcid":"https://orcid.org/0009-0005-7119-6332"},"institutions":[{"id":"https://openalex.org/I4210097554","display_name":"Center for Excellence in Brain Science and Intelligence Technology","ror":"https://ror.org/00vpwhm04","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210097554"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming Ma","raw_affiliation_strings":["Institute of Neuroscience, State Key Laboratory of Brain Cognition and Brain-inspired Intelligence Technology, Center for Excellence in Brain Science and Intelligence Technology, Chinese Academy of Sciences","University of Chinese Academy of Sciences, School of Future Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Neuroscience, State Key Laboratory of Brain Cognition and Brain-inspired Intelligence Technology, Center for Excellence in Brain Science and Intelligence Technology, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210097554"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, School of Future Technology","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100424148","display_name":"Zhipeng Wang","orcid":"https://orcid.org/0000-0001-7281-1839"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]},{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"ZhiPeng Wang","raw_affiliation_strings":["National Key Laboratory for Novel Software Technology, Nanjing University","School of Intelligence Science and Technology, Nanjing University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology, Nanjing University","institution_ids":["https://openalex.org/I881766915"]},{"raw_affiliation_string":"School of Intelligence Science and Technology, Nanjing University","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103279839","display_name":"Zhenyu Zhou","orcid":"https://orcid.org/0009-0009-8492-5222"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]},{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenyu Zhou","raw_affiliation_strings":["National Key Laboratory for Novel Software Technology, Nanjing University","School of Intelligence Science and Technology, Nanjing University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology, Nanjing University","institution_ids":["https://openalex.org/I881766915"]},{"raw_affiliation_string":"School of Intelligence Science and Technology, Nanjing University","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100719213","display_name":"Tianming Yang","orcid":"https://orcid.org/0000-0003-3700-0912"},"institutions":[{"id":"https://openalex.org/I4210097554","display_name":"Center for Excellence in Brain Science and Intelligence Technology","ror":"https://ror.org/00vpwhm04","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210097554"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianming Yang","raw_affiliation_strings":["Institute of Neuroscience, State Key Laboratory of Brain Cognition and Brain-inspired Intelligence Technology, Center for Excellence in Brain Science and Intelligence Technology, Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Neuroscience, State Key Laboratory of Brain Cognition and Brain-inspired Intelligence Technology, Center for Excellence in Brain Science and Intelligence Technology, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210097554"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017553711","display_name":"Wang-Zhou Dai","orcid":"https://orcid.org/0000-0002-6884-7158"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]},{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang-Zhou Dai","raw_affiliation_strings":["National Key Laboratory for Novel Software Technology, Nanjing University","School of Intelligence Science and Technology, Nanjing University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology, Nanjing University","institution_ids":["https://openalex.org/I881766915"]},{"raw_affiliation_string":"School of Intelligence Science and Technology, Nanjing University","institution_ids":["https://openalex.org/I36399199"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5101489985"],"corresponding_institution_ids":["https://openalex.org/I36399199","https://openalex.org/I881766915"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1222217,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6515","last_page":"6523"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.5105000138282776,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.5105000138282776,"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":0.8375999927520752},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6335999965667725},{"id":"https://openalex.org/keywords/abductive-reasoning","display_name":"Abductive reasoning","score":0.6201000213623047},{"id":"https://openalex.org/keywords/abstraction","display_name":"Abstraction","score":0.5968999862670898},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.5497000217437744},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.531499981880188}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8375999927520752},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7358999848365784},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.66839998960495},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6335999965667725},{"id":"https://openalex.org/C166088908","wikidata":"https://www.wikidata.org/wiki/Q308495","display_name":"Abductive reasoning","level":2,"score":0.6201000213623047},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.5968999862670898},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5497000217437744},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.531499981880188},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.4706000089645386},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4399000108242035},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.42669999599456787},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.3734000027179718},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.27959999442100525},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.27639999985694885},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.2694000005722046}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2025/725","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/725","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Abstraction":[0],"is":[1],"a":[2,80,110,125,150],"critical":[3],"technique":[4],"in":[5,56,64],"general":[6],"problem-solving,":[7],"allowing":[8],"complex":[9,65],"tasks":[10,66],"to":[11,27,38,97,114,124,175],"be":[12],"decomposed":[13],"into":[14],"smaller,":[15],"manageable":[16],"sub-tasks.":[17],"While":[18],"traditional":[19,176],"symbolic":[20,142],"planning":[21],"relies":[22],"on":[23,33,90],"predefined":[24,106],"primitive":[25],"symbols":[26],"construct":[28],"structured":[29],"abstractions,":[30],"its":[31],"reliance":[32],"formal":[34],"representations":[35],"limits":[36],"applicability":[37],"real-world":[39],"tasks.":[40],"On":[41],"the":[42,86,128,139,154,165,171],"other":[43],"hand,":[44],"reinforcement":[45],"learning":[46,49,146],"excels":[47],"at":[48],"end-to-end":[50,177],"policies":[51],"directly":[52,100],"from":[53,101],"sensory":[54,103],"inputs":[55,104],"unstructured":[57],"environments":[58],"but":[59,147],"struggles":[60],"with":[61,67],"compositional":[62],"generalization":[63,172],"delayed":[68,166],"rewards.":[69],"In":[70],"this":[71],"paper,":[72],"we":[73],"propose":[74],"Abductive":[75,91],"Abstract":[76],"Reinforcement":[77],"Learning":[78,92],"(A2RL),":[79],"novel":[81],"neuro-symbolic":[82],"RL":[83,95,178],"framework":[84],"bridging":[85],"two":[87],"paradigms":[88],"based":[89],"(ABL),":[93],"enabling":[94],"agents":[96],"learn":[98],"abstractions":[99],"raw":[102],"without":[105],"symbols.":[107,158],"A2RL":[108,162],"induces":[109],"finite":[111],"state":[112,122],"machine":[113],"represent":[115],"high-level,":[116],"step-by-step":[117],"procedures,":[118],"where":[119],"each":[120],"abstract":[121],"corresponds":[123],"sub-algebra":[126],"of":[127,156],"original":[129],"Markov":[130],"Decision":[131],"Process":[132],"(MDP).":[133],"This":[134],"approach":[135],"not":[136],"only":[137],"bridges":[138],"gap":[140],"between":[141],"abstraction":[143],"and":[144,169],"sub-symbolic":[145],"also":[148],"provides":[149],"natural":[151],"mechanism":[152],"for":[153],"emergence":[155],"new":[157],"Experiments":[159],"show":[160],"that":[161],"can":[163],"mitigate":[164],"reward":[167],"problem":[168],"improve":[170],"capability":[173],"compared":[174],"methods.":[179]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
