{"id":"https://openalex.org/W2965307502","doi":"https://doi.org/10.24963/ijcai.2019/324","title":"Automatic Successive Reinforcement Learning with Multiple Auxiliary Rewards","display_name":"Automatic Successive Reinforcement Learning with Multiple Auxiliary Rewards","publication_year":2019,"publication_date":"2019-07-28","ids":{"openalex":"https://openalex.org/W2965307502","doi":"https://doi.org/10.24963/ijcai.2019/324","mag":"2965307502"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2019/324","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/324","pdf_url":"https://www.ijcai.org/proceedings/2019/0324.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":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2019/0324.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036006545","display_name":"Zhaoyang Fu","orcid":"https://orcid.org/0000-0002-6107-8640"},"institutions":[{"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":"Zhao-Yang Fu","raw_affiliation_strings":["National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073912249","display_name":"De\u2010Chuan Zhan","orcid":"https://orcid.org/0000-0002-3533-2078"},"institutions":[{"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":"De-Chuan Zhan","raw_affiliation_strings":["National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086946674","display_name":"Xinchun Li","orcid":"https://orcid.org/0000-0001-9417-7971"},"institutions":[{"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":"Xin-Chun Li","raw_affiliation_strings":["National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091798623","display_name":"Yi-Xing Lu","orcid":null},"institutions":[{"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":"Yi-Xing Lu","raw_affiliation_strings":["National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I881766915"],"apc_list":null,"apc_paid":null,"fwci":0.7059,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.77912552,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"2336","last_page":"2342"},"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9952999949455261,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10524","display_name":"Traffic control and management","score":0.9812999963760376,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.9479222893714905},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6850445866584778},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6638268828392029},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.6615362167358398},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4477708339691162},{"id":"https://openalex.org/keywords/learning-classifier-system","display_name":"Learning classifier system","score":0.41253870725631714},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.4104105532169342},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12869054079055786}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9479222893714905},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6850445866584778},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6638268828392029},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.6615362167358398},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4477708339691162},{"id":"https://openalex.org/C199190896","wikidata":"https://www.wikidata.org/wiki/Q3509276","display_name":"Learning classifier system","level":3,"score":0.41253870725631714},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.4104105532169342},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12869054079055786},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2019/324","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/324","pdf_url":"https://www.ijcai.org/proceedings/2019/0324.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"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2019/324","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/324","pdf_url":"https://www.ijcai.org/proceedings/2019/0324.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":[{"id":"https://metadata.un.org/sdg/16","score":0.8500000238418579,"display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G5072222428","display_name":null,"funder_award_id":"61773198","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/W2965307502.pdf","grobid_xml":"https://content.openalex.org/works/W2965307502.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W139596442","https://openalex.org/W1515851193","https://openalex.org/W1771410628","https://openalex.org/W1777239053","https://openalex.org/W1988210060","https://openalex.org/W1995053973","https://openalex.org/W2002305926","https://openalex.org/W2060846151","https://openalex.org/W2081944499","https://openalex.org/W2095564494","https://openalex.org/W2097746659","https://openalex.org/W2116386744","https://openalex.org/W2156578004","https://openalex.org/W2164641162","https://openalex.org/W2260756217","https://openalex.org/W2278712528","https://openalex.org/W2556958149","https://openalex.org/W2625456521","https://openalex.org/W2736601468","https://openalex.org/W2963095800","https://openalex.org/W2963758131","https://openalex.org/W2964043796","https://openalex.org/W4293872189","https://openalex.org/W4394666657","https://openalex.org/W6642904842","https://openalex.org/W6674687940","https://openalex.org/W6864014924"],"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/W4383501708","https://openalex.org/W2130711276","https://openalex.org/W3135573334"],"abstract_inverted_index":{"Reinforcement":[0,79],"learning":[1,32,47,65,90],"has":[2],"played":[3],"an":[4],"important":[5],"role":[6],"in":[7,69],"decision":[8],"making":[9],"related":[10],"applications,":[11],"e.g.,":[12],"robotics":[13],"motion,":[14],"self-driving,":[15],"recommendation,":[16],"etc.":[17],"The":[18],"reward":[19],"function,":[20],"as":[21],"a":[22,34,105],"crucial":[23],"component,":[24],"affects":[25],"the":[26,43,64,76,98],"efficiency":[27],"and":[28,67,72,94,114,118],"effectiveness":[29,68],"of":[30,45,100,107],"reinforcement":[31,46,89],"to":[33],"large":[35],"extent.":[36],"In":[37],"this":[38],"paper,":[39],"we":[40,74],"focus":[41],"on":[42,104],"investigation":[44],"with":[48],"more":[49],"than":[50],"one":[51],"auxiliary":[52,59,83],"reward.":[53],"It":[54],"is":[55],"found":[56],"that":[57],"different":[58,70],"rewards":[60,84],"can":[61],"boost":[62],"up":[63],"rate":[66],"stages,":[71],"consequently":[73],"propose":[75],"Automatic":[77],"Successive":[78],"Learning":[80],"(ASR)":[81],"for":[82,87],"grading":[85],"selection":[86],"efficient":[88],"by":[91],"stages.":[92],"Experiments":[93],"simulations":[95],"have":[96],"shown":[97],"superiority":[99],"our":[101],"proposed":[102],"ASR":[103],"range":[106],"environments,":[108],"including":[109],"OpenAI":[110],"classical":[111],"control":[112],"domains":[113],"video":[115],"games;":[116],"Freeway":[117],"Catcher.":[119]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}