{"id":"https://openalex.org/W3034311880","doi":"https://doi.org/10.24963/ijcai.2020/317","title":"KoGuN: Accelerating Deep Reinforcement Learning via Integrating Human Suboptimal Knowledge","display_name":"KoGuN: Accelerating Deep Reinforcement Learning via Integrating Human Suboptimal Knowledge","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3034311880","doi":"https://doi.org/10.24963/ijcai.2020/317","mag":"3034311880"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2020/317","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/317","pdf_url":"https://www.ijcai.org/proceedings/2020/0317.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2020/0317.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100364209","display_name":"Peng Zhang","orcid":"https://orcid.org/0000-0003-0228-9330"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]},{"id":"https://openalex.org/I4210159102","display_name":"Huawei Technologies (Sweden)","ror":"https://ror.org/0500fyd17","country_code":"SE","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210159102"]}],"countries":["CN","SE"],"is_corresponding":false,"raw_author_name":"Peng Zhang","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University","Noah's Ark Lab, Huawei","College of Intelligence and Computing, Tianjin University; Noah's Ark Lab, Huawei"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"Noah's Ark Lab, Huawei","institution_ids":["https://openalex.org/I4210159102"]},{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University; Noah's Ark Lab, Huawei","institution_ids":["https://openalex.org/I162868743","https://openalex.org/I4210159102"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047509839","display_name":"Jianye Hao","orcid":"https://orcid.org/0000-0002-0422-8235"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]},{"id":"https://openalex.org/I4210159102","display_name":"Huawei Technologies (Sweden)","ror":"https://ror.org/0500fyd17","country_code":"SE","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210159102"]}],"countries":["CN","SE"],"is_corresponding":false,"raw_author_name":"Jianye Hao","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University","Noah's Ark Lab, Huawei","Tianjin Key Lab of Machine Learning"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"Noah's Ark Lab, Huawei","institution_ids":["https://openalex.org/I4210159102"]},{"raw_affiliation_string":"Tianjin Key Lab of Machine Learning","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082417441","display_name":"Weixun Wang","orcid":"https://orcid.org/0000-0002-2727-8948"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weixun Wang","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103176048","display_name":"Hongyao Tang","orcid":"https://orcid.org/0000-0001-7478-7684"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongyao Tang","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101601194","display_name":"Yi Ma","orcid":"https://orcid.org/0000-0003-1832-8920"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Ma","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019579988","display_name":"Yihai Duan","orcid":null},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yihai Duan","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084937471","display_name":"Yan Zheng","orcid":"https://orcid.org/0000-0003-2741-058X"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Zheng","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University","institution_ids":["https://openalex.org/I162868743"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2291","last_page":"2297"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9965000152587891,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T12676","display_name":"Machine Learning and ELM","score":0.9829000234603882,"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":0.8839244842529297},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8101024031639099},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.6329014301300049},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6105654835700989},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.603877067565918},{"id":"https://openalex.org/keywords/learning-classifier-system","display_name":"Learning classifier system","score":0.5193511247634888},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5180085301399231},{"id":"https://openalex.org/keywords/scratch","display_name":"Scratch","score":0.4746285676956177},{"id":"https://openalex.org/keywords/fuzzy-logic","display_name":"Fuzzy logic","score":0.41783463954925537},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.4156317710876465},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10336005687713623}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8839244842529297},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8101024031639099},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6329014301300049},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6105654835700989},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.603877067565918},{"id":"https://openalex.org/C199190896","wikidata":"https://www.wikidata.org/wiki/Q3509276","display_name":"Learning classifier system","level":3,"score":0.5193511247634888},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5180085301399231},{"id":"https://openalex.org/C2781235140","wikidata":"https://www.wikidata.org/wiki/Q275131","display_name":"Scratch","level":2,"score":0.4746285676956177},{"id":"https://openalex.org/C58166","wikidata":"https://www.wikidata.org/wiki/Q224821","display_name":"Fuzzy logic","level":2,"score":0.41783463954925537},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.4156317710876465},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10336005687713623},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"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/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2020/317","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/317","pdf_url":"https://www.ijcai.org/proceedings/2020/0317.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2020/317","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/317","pdf_url":"https://www.ijcai.org/proceedings/2020/0317.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8921145797","display_name":null,"funder_award_id":"U1836214","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3034311880.pdf","grobid_xml":"https://content.openalex.org/works/W3034311880.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1191599655","https://openalex.org/W1522301498","https://openalex.org/W1545139845","https://openalex.org/W1590762254","https://openalex.org/W1771410628","https://openalex.org/W1966102928","https://openalex.org/W2051228319","https://openalex.org/W2089217417","https://openalex.org/W2145339207","https://openalex.org/W2257979135","https://openalex.org/W2607198029","https://openalex.org/W2736601468","https://openalex.org/W2749928749","https://openalex.org/W2923924002","https://openalex.org/W2952230511","https://openalex.org/W2963277051","https://openalex.org/W2963687836","https://openalex.org/W4236304806","https://openalex.org/W4255862580","https://openalex.org/W4394642966"],"related_works":["https://openalex.org/W1966456942","https://openalex.org/W2754028433","https://openalex.org/W3148138296","https://openalex.org/W1882507001","https://openalex.org/W2367922714","https://openalex.org/W1986508893","https://openalex.org/W2352650970","https://openalex.org/W2130711276","https://openalex.org/W2786230833","https://openalex.org/W3135573334"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,23,52,69,83,148,175],"agents":[2],"usually":[3],"learn":[4],"from":[5,21],"scratch,":[6],"which":[7,164],"requires":[8],"a":[9,30,80,102,118,127],"large":[10],"number":[11],"of":[12,25,82,117,177],"interactions":[13],"with":[14,29,111,144,182],"the":[15,22,36,41,51,56,65,68,76],"environment.":[16],"This":[17],"is":[18,71,138],"quite":[19],"different":[20],"process":[24,53,70],"human.":[26],"When":[27],"faced":[28],"new":[31,66],"task,":[32,67],"human":[33,107,124,167,185],"naturally":[34],"have":[35],"common":[37],"sense":[38],"and":[39,49,84,126,140,169],"use":[40],"prior":[42,57,108,133,186],"knowledge":[43,58,97,110,125,168],"to":[44,64,88,122,130],"derive":[45],"an":[46],"initial":[47,77],"policy":[48,78,99],"guide":[50],"afterwards.":[54],"Although":[55],"may":[59],"be":[60,142],"not":[61],"fully":[62],"applicable":[63],"significantly":[72],"sped":[73],"up":[74],"since":[75],"ensures":[79],"quick-start":[81],"intermediate":[85],"guidance":[86],"allows":[87],"avoid":[89],"unnecessary":[90],"exploration.":[91],"Taking":[92],"this":[93],"inspiration,":[94],"we":[95],"propose":[96],"guided":[98],"network":[100],"(KoGuN),":[101],"novel":[103],"framework":[104,115,137],"that":[105,161],"combines":[106,165],"suboptimal":[109,132,166],"reinforcement":[112,147],"learning.":[113],"Our":[114],"consists":[116],"fuzzy":[119],"rule":[120],"controller":[121],"represent":[123],"refine":[128],"module":[129],"finetune":[131],"knowledge.":[134,187],"The":[135,157],"proposed":[136],"end-to-end":[139],"can":[141],"combined":[143],"existing":[145],"policy-based":[146],"algorithm.":[149],"We":[150],"conduct":[151],"experiments":[152],"on":[153,174],"several":[154],"control":[155],"tasks.":[156],"empirical":[158],"results":[159],"show":[160],"our":[162],"approach,":[163],"RL,":[170],"achieves":[171],"significant":[172],"improvement":[173],"efficiency":[176],"flat":[178],"RL":[179],"algorithms,":[180],"even":[181],"very":[183],"low-performance":[184]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}