{"id":"https://openalex.org/W4205779441","doi":"https://doi.org/10.1109/tg.2021.3134259","title":"Deep Reinforcement Learning With Part-Aware Exploration Bonus in Video Games","display_name":"Deep Reinforcement Learning With Part-Aware Exploration Bonus in Video Games","publication_year":2021,"publication_date":"2021-12-13","ids":{"openalex":"https://openalex.org/W4205779441","doi":"https://doi.org/10.1109/tg.2021.3134259"},"language":"en","primary_location":{"id":"doi:10.1109/tg.2021.3134259","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tg.2021.3134259","pdf_url":null,"source":{"id":"https://openalex.org/S4210224842","display_name":"IEEE Transactions on Games","issn_l":"2475-1502","issn":["2475-1502","2475-1510"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Games","raw_type":"journal-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/A5101814011","display_name":"Pei Xu","orcid":"https://orcid.org/0000-0003-1766-5634"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","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/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"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":"Pei Xu","raw_affiliation_strings":["School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","Center for Research on Intelligent System and Engineering, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-1766-5634","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210165038"]},{"raw_affiliation_string":"Center for Research on Intelligent System and Engineering, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083652259","display_name":"Qiyue Yin","orcid":"https://orcid.org/0000-0002-3442-6275"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","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":"Qiyue Yin","raw_affiliation_strings":["Center for Research on Intelligent System and Engineering, Institute of Automation, Chinese Academy of Sciences, Beijing, China","University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-3442-6275","affiliations":[{"raw_affiliation_string":"Center for Research on Intelligent System and Engineering, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109012644","display_name":"Junge Zhang","orcid":"https://orcid.org/0000-0002-9970-394X"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","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":"Junge Zhang","raw_affiliation_strings":["Center for Research on Intelligent System and Engineering, Institute of Automation, Chinese Academy of Sciences, Beijing, China","University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-9970-394X","affiliations":[{"raw_affiliation_string":"Center for Research on Intelligent System and Engineering, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028693655","display_name":"Kaiqi Huang","orcid":"https://orcid.org/0000-0002-2677-9273"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","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/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":"Kaiqi Huang","raw_affiliation_strings":["Center for Research on Intelligent System and Engineering and the National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China","University of Chinese Academy of Sciences, Beijing, China","CAS Center for Excellence in Brain Science and Intelligence Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-2677-9273","affiliations":[{"raw_affiliation_string":"Center for Research on Intelligent System and Engineering and the National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"CAS Center for Excellence in Brain Science and Intelligence Technology, Beijing, China","institution_ids":["https://openalex.org/I4210097554"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9795,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.81394423,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"14","issue":"4","first_page":"644","last_page":"653"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994000196456909,"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":0.9994000196456909,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.9700000286102295,"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/T11197","display_name":"Digital Games and Media","score":0.9248999953269958,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7765485048294067},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7090528011322021},{"id":"https://openalex.org/keywords/randomness","display_name":"Randomness","score":0.6681989431381226},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.656446635723114},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6442532539367676},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5964742302894592},{"id":"https://openalex.org/keywords/curiosity","display_name":"Curiosity","score":0.5492097735404968},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5263729691505432},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4835379123687744},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4527114927768707},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4326953589916229},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09100022912025452}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7765485048294067},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7090528011322021},{"id":"https://openalex.org/C125112378","wikidata":"https://www.wikidata.org/wiki/Q176640","display_name":"Randomness","level":2,"score":0.6681989431381226},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.656446635723114},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6442532539367676},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5964742302894592},{"id":"https://openalex.org/C33435437","wikidata":"https://www.wikidata.org/wiki/Q366791","display_name":"Curiosity","level":2,"score":0.5492097735404968},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5263729691505432},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4835379123687744},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4527114927768707},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4326953589916229},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09100022912025452},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tg.2021.3134259","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tg.2021.3134259","pdf_url":null,"source":{"id":"https://openalex.org/S4210224842","display_name":"IEEE Transactions on Games","issn_l":"2475-1502","issn":["2475-1502","2475-1510"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Games","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6431871145","display_name":null,"funder_award_id":"61721004","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G852446924","display_name":null,"funder_award_id":"61876181","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"},{"id":"https://openalex.org/F4320321133","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35"},{"id":"https://openalex.org/F4320335892","display_name":"Youth Innovation Promotion Association","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":63,"referenced_works":["https://openalex.org/W172298727","https://openalex.org/W779494576","https://openalex.org/W1934410531","https://openalex.org/W2145339207","https://openalex.org/W2155027007","https://openalex.org/W2184393491","https://openalex.org/W2195446438","https://openalex.org/W2280163991","https://openalex.org/W2553347458","https://openalex.org/W2556477470","https://openalex.org/W2596982695","https://openalex.org/W2603088459","https://openalex.org/W2623491082","https://openalex.org/W2625219738","https://openalex.org/W2724169821","https://openalex.org/W2736601468","https://openalex.org/W2805623918","https://openalex.org/W2885550588","https://openalex.org/W2899077443","https://openalex.org/W2907502844","https://openalex.org/W2950794298","https://openalex.org/W2950872548","https://openalex.org/W2953772919","https://openalex.org/W2963276097","https://openalex.org/W2963523627","https://openalex.org/W2963761387","https://openalex.org/W2964043796","https://openalex.org/W2964067469","https://openalex.org/W3012502279","https://openalex.org/W3034956653","https://openalex.org/W3101438731","https://openalex.org/W3106250896","https://openalex.org/W3199151886","https://openalex.org/W4287867830","https://openalex.org/W4295720520","https://openalex.org/W6607097208","https://openalex.org/W6622487243","https://openalex.org/W6683204974","https://openalex.org/W6686211706","https://openalex.org/W6687590523","https://openalex.org/W6692846177","https://openalex.org/W6695011786","https://openalex.org/W6717230150","https://openalex.org/W6729556111","https://openalex.org/W6730127522","https://openalex.org/W6730153900","https://openalex.org/W6735033012","https://openalex.org/W6735789912","https://openalex.org/W6735865323","https://openalex.org/W6739193204","https://openalex.org/W6740092555","https://openalex.org/W6741002519","https://openalex.org/W6753925943","https://openalex.org/W6755654293","https://openalex.org/W6756303580","https://openalex.org/W6757797181","https://openalex.org/W6762863188","https://openalex.org/W6763704883","https://openalex.org/W6771418060","https://openalex.org/W6771807793","https://openalex.org/W6775522024","https://openalex.org/W6780559895","https://openalex.org/W6785652829"],"related_works":["https://openalex.org/W4296474751","https://openalex.org/W3046262286","https://openalex.org/W3085832734","https://openalex.org/W4319083788","https://openalex.org/W3022038857","https://openalex.org/W4360764167","https://openalex.org/W2151702863","https://openalex.org/W4318621078","https://openalex.org/W3095449511","https://openalex.org/W3141495010"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,160,176],"algorithms":[2],"rely":[3],"on":[4,154,168],"carefully":[5],"engineering":[6],"environment":[7],"rewards":[8,18,61,109,156],"that":[9,28,92],"are":[10,19,29,93],"extrinsic":[11],"to":[12,31,58,74,105,138],"agents.":[13,32],"However,":[14,81],"environments":[15],"with":[16,96],"dense":[17],"rare,":[20],"motivating":[21],"the":[22,44,54,65,90,99,119,144,150,159,173,190],"need":[23],"for":[24,110,126],"developing":[25],"reward":[26,40,49],"functions":[27],"intrinsic":[30,39,60,155],"Curiosity":[33],"is":[34,62,136,187],"a":[35,70],"type":[36],"of":[37,89,98,121,152,162,189],"successful":[38],"function,":[41],"which":[42,101,186],"uses":[43],"prediction":[45,55],"error":[46],"as":[47],"an":[48,132],"signal.":[50],"In":[51,113],"prior":[52,123],"work,":[53],"problem":[56],"used":[57],"generate":[59,106],"optimized":[63],"in":[64,195],"pixel":[66],"space":[67,73],"rather":[68],"than":[69],"learnable":[71],"feature":[72,79,146],"avoid":[75],"randomness":[76,153],"caused":[77,157],"by":[78,158],"changes.":[80],"these":[82],"methods":[83],"ignore":[84],"small":[85],"but":[86],"important":[87],"elements":[88],"states":[91],"often":[94],"associated":[95],"locations":[97],"character,":[100],"makes":[102],"it":[103],"impossible":[104],"accurate":[107],"internal":[108],"efficient":[111],"exploration.":[112],"this":[114],"article,":[115],"we":[116],"first":[117],"demonstrate":[118],"effectiveness":[120],"introducing":[122],"learned":[124,140,145],"features":[125],"existing":[127],"prediction-based":[128],"exploration":[129,193],"methods.":[130],"Then,":[131],"attention":[133],"map":[134],"mechanism":[135],"designed":[137],"discretize":[139],"features,":[141],"thereby":[142],"updating":[143],"and":[147],"meanwhile":[148],"reducing":[149],"impact":[151],"process":[161],"features.":[163],"We":[164],"verify":[165],"our":[166],"method":[167],"some":[169],"video":[170],"games":[171],"from":[172],"standard":[174],"reinforcement":[175],"Atari":[177,198],"benchmark,":[178],"achieving":[179],"clear":[180],"improvements":[181],"over":[182],"random":[183],"network":[184],"distillation,":[185],"one":[188],"most":[191],"advanced":[192],"methods,":[194],"almost":[196],"all":[197],"games.":[199]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}