{"id":"https://openalex.org/W3203577688","doi":"https://doi.org/10.1109/ijcnn52387.2021.9534251","title":"Learning to Play Hard Exploration Games Using Graph-Guided Self-Navigation","display_name":"Learning to Play Hard Exploration Games Using Graph-Guided Self-Navigation","publication_year":2021,"publication_date":"2021-07-18","ids":{"openalex":"https://openalex.org/W3203577688","doi":"https://doi.org/10.1109/ijcnn52387.2021.9534251","mag":"3203577688"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn52387.2021.9534251","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn52387.2021.9534251","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Joint Conference on Neural Networks (IJCNN)","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/A5055979604","display_name":"Enmin Zhao","orcid":"https://orcid.org/0000-0001-6117-5080"},"institutions":[{"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"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Enmin Zhao","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, Beijing, P. R. China","School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, P. R. China"],"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, Beijing, P. R. China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, P. R. China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089763177","display_name":"Renye Yan","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"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":"Renye Yan","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, Beijing, P. R. China","School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, P. R. China"],"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, Beijing, P. R. China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, P. R. China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100400000","display_name":"Kai Li","orcid":"https://orcid.org/0000-0003-3840-3270"},"institutions":[{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Li","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, Beijing, P. R. China"],"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, Beijing, P. R. China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100419693","display_name":"Lijuan Li","orcid":"https://orcid.org/0000-0002-2758-7433"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lijuan Li","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, Beijing, P. R. China"],"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, Beijing, P. R. China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076090670","display_name":"Junliang Xing","orcid":"https://orcid.org/0000-0001-6801-0510"},"institutions":[{"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"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junliang Xing","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, Beijing, P. R. China","School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, P. R. China"],"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, Beijing, P. R. China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, P. R. China","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5055979604"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210094879","https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":0.136,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.55498842,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"518","issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.995199978351593,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11574","display_name":"Artificial Intelligence in Games","score":0.9919000267982483,"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":0.8015198707580566},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7848529815673828},{"id":"https://openalex.org/keywords/curiosity","display_name":"Curiosity","score":0.6445830464363098},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.60129314661026},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5638203024864197},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5251911878585815},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.44999468326568604},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.434996098279953},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.42165881395339966},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3692413568496704},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.34361183643341064},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08226841688156128},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07909280061721802}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8015198707580566},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7848529815673828},{"id":"https://openalex.org/C33435437","wikidata":"https://www.wikidata.org/wiki/Q366791","display_name":"Curiosity","level":2,"score":0.6445830464363098},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.60129314661026},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5638203024864197},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5251911878585815},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.44999468326568604},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.434996098279953},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.42165881395339966},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3692413568496704},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.34361183643341064},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08226841688156128},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07909280061721802},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn52387.2021.9534251","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn52387.2021.9534251","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Life below water","score":0.44999998807907104,"id":"https://metadata.un.org/sdg/14"}],"awards":[{"id":"https://openalex.org/G190366668","display_name":null,"funder_award_id":"62076238,61902402","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3423044344","display_name":null,"funder_award_id":"RAGR20200104","funder_id":"https://openalex.org/F4320316083","funder_display_name":"Tencent"},{"id":"https://openalex.org/G5820763317","display_name":null,"funder_award_id":"2019AAA010340X","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G622688436","display_name":null,"funder_award_id":"XDA27000000","funder_id":"https://openalex.org/F4320321133","funder_display_name":"Chinese Academy of Sciences"}],"funders":[{"id":"https://openalex.org/F4320316083","display_name":"Tencent","ror":"https://ror.org/00hhjss72"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321133","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":72,"referenced_works":["https://openalex.org/W112666333","https://openalex.org/W1771410628","https://openalex.org/W1850531616","https://openalex.org/W1931877416","https://openalex.org/W1999874108","https://openalex.org/W2094695465","https://openalex.org/W2113023245","https://openalex.org/W2145339207","https://openalex.org/W2170899200","https://openalex.org/W2173564293","https://openalex.org/W2280163991","https://openalex.org/W2556477470","https://openalex.org/W2594640072","https://openalex.org/W2596982695","https://openalex.org/W2626429629","https://openalex.org/W2736601468","https://openalex.org/W2751973545","https://openalex.org/W2788862220","https://openalex.org/W2803616302","https://openalex.org/W2804380964","https://openalex.org/W2807192342","https://openalex.org/W2895453875","https://openalex.org/W2899077443","https://openalex.org/W2904157920","https://openalex.org/W2913343212","https://openalex.org/W2949475445","https://openalex.org/W2950735232","https://openalex.org/W2951799221","https://openalex.org/W2953100042","https://openalex.org/W2962715211","https://openalex.org/W2962957031","https://openalex.org/W2963095800","https://openalex.org/W2963126744","https://openalex.org/W2963160877","https://openalex.org/W2963177395","https://openalex.org/W2963276097","https://openalex.org/W2963277051","https://openalex.org/W2963376229","https://openalex.org/W2963523627","https://openalex.org/W2963938771","https://openalex.org/W2964043796","https://openalex.org/W2964062135","https://openalex.org/W2964067469","https://openalex.org/W2964185768","https://openalex.org/W3018036994","https://openalex.org/W3129322645","https://openalex.org/W4297664295","https://openalex.org/W4300198501","https://openalex.org/W6604566608","https://openalex.org/W6638018090","https://openalex.org/W6639056794","https://openalex.org/W6640174482","https://openalex.org/W6676728370","https://openalex.org/W6685444567","https://openalex.org/W6692846177","https://openalex.org/W6695011786","https://openalex.org/W6717230150","https://openalex.org/W6718092244","https://openalex.org/W6730111887","https://openalex.org/W6730641667","https://openalex.org/W6734205138","https://openalex.org/W6735033012","https://openalex.org/W6741002519","https://openalex.org/W6748645729","https://openalex.org/W6751285671","https://openalex.org/W6751540476","https://openalex.org/W6751955673","https://openalex.org/W6754957883","https://openalex.org/W6755654293","https://openalex.org/W6756303580","https://openalex.org/W6757288412","https://openalex.org/W6758641611"],"related_works":["https://openalex.org/W3094054656","https://openalex.org/W4285676344","https://openalex.org/W2123270665","https://openalex.org/W4382584175","https://openalex.org/W2060310955","https://openalex.org/W2284924956","https://openalex.org/W3043413210","https://openalex.org/W2613740288","https://openalex.org/W4252460700","https://openalex.org/W4383268304"],"abstract_inverted_index":{"This":[0],"work":[1],"considers":[2],"the":[3,47,54,59,64,77,103,106],"problem":[4],"of":[5,105],"deep":[6,92],"reinforcement":[7],"learning":[8],"(RL)":[9],"with":[10],"long":[11],"time":[12],"dependencies":[13],"and":[14,58,112],"sparse":[15],"rewards,":[16],"as":[17],"are":[18,86],"found":[19],"in":[20],"many":[21],"hard":[22,98],"exploration":[23,79,99],"games.":[24],"A":[25],"graph-based":[26],"representation":[27,42],"is":[28,81],"proposed":[29,107],"to":[30,34,66,118],"allow":[31],"an":[32],"agent":[33,55,65],"perform":[35],"self-navigation":[36],"for":[37,73],"environmental":[38],"exploration.":[39],"The":[40,109],"graph":[41],"not":[43],"only":[44],"effectively":[45,87],"models":[46,114],"environment":[48],"structure,":[49],"but":[50],"also":[51],"efficiently":[52],"traces":[53],"state":[56],"changes":[57],"corresponding":[60],"actions.":[61],"By":[62],"encouraging":[63],"earn":[67],"a":[68,90],"new":[69,74],"influence-based":[70],"curiosity":[71],"reward":[72],"game":[75],"observations,":[76],"whole":[78],"task":[80],"divided":[82],"into":[83],"sub-tasks,":[84],"which":[85],"solved":[88],"using":[89],"unified":[91],"RL":[93],"model.":[94],"Experimental":[95],"evaluations":[96],"on":[97,122],"Atari":[100],"Games":[101],"demonstrate":[102],"effectiveness":[104],"method.":[108],"source":[110],"code":[111],"learned":[113],"will":[115],"be":[116],"released":[117],"facilitate":[119],"further":[120],"studies":[121],"this":[123],"problem.":[124]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}