{"id":"https://openalex.org/W2965871673","doi":"https://doi.org/10.24963/ijcai.2019/481","title":"Solving Continual Combinatorial Selection via Deep Reinforcement Learning","display_name":"Solving Continual Combinatorial Selection via Deep Reinforcement Learning","publication_year":2019,"publication_date":"2019-07-28","ids":{"openalex":"https://openalex.org/W2965871673","doi":"https://doi.org/10.24963/ijcai.2019/481","mag":"2965871673"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2019/481","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/481","pdf_url":"https://www.ijcai.org/proceedings/2019/0481.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2019/0481.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5022740088","display_name":"Hyungseok Song","orcid":"https://orcid.org/0000-0002-4534-0274"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyungseok Song","raw_affiliation_strings":["School of Electrical Engineering, KAIST, Daejeon, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, KAIST, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056471397","display_name":"Hyeryung Jang","orcid":"https://orcid.org/0000-0002-7314-0739"},"institutions":[{"id":"https://openalex.org/I183935753","display_name":"King's College London","ror":"https://ror.org/0220mzb33","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I183935753"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Hyeryung Jang","raw_affiliation_strings":["Informatics, King\u2019s College London, London, United Kingdom","Informatics, King's College London, London, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Informatics, King\u2019s College London, London, United Kingdom","institution_ids":["https://openalex.org/I183935753"]},{"raw_affiliation_string":"Informatics, King's College London, London, United Kingdom","institution_ids":["https://openalex.org/I183935753"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052987262","display_name":"Ha\u00ef Tran","orcid":"https://orcid.org/0000-0002-4006-3909"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hai H. Tran","raw_affiliation_strings":["School of Electrical Engineering, KAIST, Daejeon, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, KAIST, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054796820","display_name":"Se-eun Yoon","orcid":"https://orcid.org/0009-0004-7653-7012"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Se-eun Yoon","raw_affiliation_strings":["School of Electrical Engineering, KAIST, Daejeon, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, KAIST, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102364671","display_name":"Kyunghwan Son","orcid":null},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kyunghwan Son","raw_affiliation_strings":["School of Electrical Engineering, KAIST, Daejeon, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, KAIST, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063019879","display_name":"Donggyu Yun","orcid":null},"institutions":[{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Donggyu Yun","raw_affiliation_strings":["Naver Corporation, Seongnam, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Naver Corporation, Seongnam, South Korea","institution_ids":["https://openalex.org/I60922564"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111947421","display_name":"Hyoju Chung","orcid":null},"institutions":[{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyoju Chung","raw_affiliation_strings":["Naver Corporation, Seongnam, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Naver Corporation, Seongnam, South Korea","institution_ids":["https://openalex.org/I60922564"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037245619","display_name":"Yung Yi","orcid":"https://orcid.org/0000-0002-6955-3135"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yung Yi","raw_affiliation_strings":["School of Electrical Engineering, KAIST, Daejeon, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, KAIST, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3467","last_page":"3474"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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"}},{"id":"https://openalex.org/T10906","display_name":"AI-based Problem Solving and Planning","score":0.9900000095367432,"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"}},{"id":"https://openalex.org/T12288","display_name":"Optimization and Search Problems","score":0.9873999953269958,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.882928192615509},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.865608811378479},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7106937766075134},{"id":"https://openalex.org/keywords/action-selection","display_name":"Action selection","score":0.6040910482406616},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5789815187454224},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5755118131637573},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.5627996325492859},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5225010514259338},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.522068202495575},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4757630228996277},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.46618813276290894},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4598032534122467},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.43724849820137024},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2956962585449219},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.22725287079811096}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.882928192615509},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.865608811378479},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7106937766075134},{"id":"https://openalex.org/C166109690","wikidata":"https://www.wikidata.org/wiki/Q4677422","display_name":"Action selection","level":3,"score":0.6040910482406616},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5789815187454224},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5755118131637573},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.5627996325492859},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5225010514259338},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.522068202495575},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4757630228996277},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.46618813276290894},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4598032534122467},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.43724849820137024},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2956962585449219},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22725287079811096},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.24963/ijcai.2019/481","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/481","pdf_url":"https://www.ijcai.org/proceedings/2019/0481.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1909.03638","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1909.03638","pdf_url":"https://arxiv.org/pdf/1909.03638","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"pmh:oai:kclpure.kcl.ac.uk:publications/5b2365a2-d797-4121-941b-a0c1df39a76c","is_oa":false,"landing_page_url":"https://kclpure.kcl.ac.uk/portal/en/publications/5b2365a2-d797-4121-941b-a0c1df39a76c","pdf_url":null,"source":{"id":"https://openalex.org/S4306400216","display_name":"Research Portal (King's College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I183935753","host_organization_name":"King's College London","host_organization_lineage":["https://openalex.org/I183935753"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Song, H, Jang, H, Tran, H H, Yoon, S E, Son, K, Yun, D, Chung, H & Yi, Y 2019, Solving continual combinatorial selection via deep reinforcement learning. in S Kraus (ed.), Proceedings of the 28th International Joint Conference on Artificial Intelligence, IJCAI 2019. vol. 2019-August, pp. 3467-3474, 28th International Joint Conference on Artificial Intelligence, IJCAI 2019, Macao, China, 10/08/2019.","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2019/481","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/481","pdf_url":"https://www.ijcai.org/proceedings/2019/0481.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.8199999928474426}],"awards":[{"id":"https://openalex.org/G6056310901","display_name":null,"funder_award_id":"2016-0-00160","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2965871673.pdf","grobid_xml":"https://content.openalex.org/works/W2965871673.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W1604363237","https://openalex.org/W1989799721","https://openalex.org/W2103496339","https://openalex.org/W2121877077","https://openalex.org/W2145339207","https://openalex.org/W2200988052","https://openalex.org/W2400213106","https://openalex.org/W2443763917","https://openalex.org/W2560609797","https://openalex.org/W2594345251","https://openalex.org/W2607264901","https://openalex.org/W2751379610","https://openalex.org/W2753798143","https://openalex.org/W2787933113","https://openalex.org/W2793523712","https://openalex.org/W2799020113","https://openalex.org/W2805798351","https://openalex.org/W2907805623","https://openalex.org/W2912555327","https://openalex.org/W2919013397","https://openalex.org/W2952689920","https://openalex.org/W2962988969","https://openalex.org/W2963446085","https://openalex.org/W2963586744","https://openalex.org/W2963658727","https://openalex.org/W2963887288","https://openalex.org/W2964015378","https://openalex.org/W2964072429","https://openalex.org/W4288621401","https://openalex.org/W4300314841"],"related_works":["https://openalex.org/W4400868993","https://openalex.org/W3096874164","https://openalex.org/W1985560493","https://openalex.org/W2386410636","https://openalex.org/W2357975469","https://openalex.org/W2145363145","https://openalex.org/W1626977535","https://openalex.org/W2341346307","https://openalex.org/W3168977894","https://openalex.org/W2015051472"],"abstract_inverted_index":{"We":[0],"consider":[1],"the":[2,17,41,62,69,81,104,109,152],"Markov":[3],"Decision":[4],"Process":[5],"(MDP)":[6],"of":[7,11,26,43,85,93,106,111,115],"selecting":[8,94],"a":[9,52,90,126],"subset":[10],"items":[12,44,96],"at":[13,108],"each":[14],"step,":[15],"termed":[16],"Select-MDP":[18,75],"(S-MDP).":[19],"The":[20],"large":[21,156],"state":[22,121],"and":[23,157],"action":[24,92],"spaces":[25,165],"S-MDPs":[27],"make":[28],"them":[29],"intractable":[30],"to":[31,56,80,161],"solve":[32,57],"with":[33,131,163],"typical":[34],"reinforcement":[35],"learning":[36],"(RL)":[37],"algorithms":[38],"especially":[39],"when":[40,151],"number":[42],"is":[45,78,155],"huge.":[46],"In":[47],"this":[48,58,120],"paper,":[49],"we":[50,67,118],"present":[51],"deep":[53],"RL":[54],"algorithm":[55],"issue":[59],"by":[60,124],"adopting":[61],"following":[63],"key":[64],"ideas.":[65],"First,":[66],"convert":[68],"original":[70],"S-MDP":[71,82],"into":[72,98],"an":[73,112],"Iterative":[74],"(IS-MDP),":[76],"which":[77,136],"equivalent":[79],"in":[83,103,129,170],"terms":[84],"optimal":[86],"actions.":[87],"IS-MDP":[88],"decomposes":[89],"joint":[91],"K":[95,99],"simultaneously":[97],"iterative":[100],"selections":[101],"resulting":[102],"decrease":[105],"actions":[107],"expense":[110],"exponential":[113],"increase":[114],"states.":[116],"Second,":[117],"overcome":[119],"space":[122,154],"explosion":[123],"exploiting":[125],"special":[127],"symmetry":[128],"IS-MDPs":[130],"novel":[132],"weight":[133],"shared":[134],"Q-networks,":[135],"provably":[137],"maintain":[138],"sufficient":[139],"expressive":[140],"power.":[141],"Various":[142],"experiments":[143],"demonstrate":[144],"that":[145,158],"our":[146],"approach":[147],"works":[148],"well":[149],"even":[150],"item":[153,164],"it":[159],"scales":[160],"environments":[162],"different":[166],"from":[167],"those":[168],"used":[169],"training.":[171]},"counts_by_year":[{"year":2023,"cited_by_count":4},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}