{"id":"https://openalex.org/W4402508398","doi":"https://doi.org/10.1109/tcds.2024.3460368","title":"Neighborhood-Curiosity-Based Exploration in Multiagent Reinforcement Learning","display_name":"Neighborhood-Curiosity-Based Exploration in Multiagent Reinforcement Learning","publication_year":2024,"publication_date":"2024-09-13","ids":{"openalex":"https://openalex.org/W4402508398","doi":"https://doi.org/10.1109/tcds.2024.3460368"},"language":"en","primary_location":{"id":"doi:10.1109/tcds.2024.3460368","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcds.2024.3460368","pdf_url":null,"source":{"id":"https://openalex.org/S2488537894","display_name":"IEEE Transactions on Cognitive and Developmental Systems","issn_l":"2379-8920","issn":["2379-8920","2379-8939"],"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 Cognitive and Developmental Systems","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/A5008475651","display_name":"Shike Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shike Yang","raw_affiliation_strings":["School of Cybersecurity, Northwestern Polytechnical University, Xi’an, China"],"raw_orcid":"https://orcid.org/0009-0006-2033-0535","affiliations":[{"raw_affiliation_string":"School of Cybersecurity, Northwestern Polytechnical University, Xi’an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100613787","display_name":"Ziming He","orcid":"https://orcid.org/0009-0003-2218-8550"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziming He","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University, Xi’an, China"],"raw_orcid":"https://orcid.org/0009-0003-2218-8550","affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, Xi’an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037024339","display_name":"Jingchen Li","orcid":"https://orcid.org/0000-0003-0905-0816"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingchen Li","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University, Xi’an, China"],"raw_orcid":"https://orcid.org/0000-0003-0905-0816","affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, Xi’an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013665827","display_name":"Haobin Shi","orcid":"https://orcid.org/0000-0003-2180-8941"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haobin Shi","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University, Xi’an, China"],"raw_orcid":"https://orcid.org/0000-0003-2180-8941","affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, Xi’an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045779375","display_name":"Qingbing Ji","orcid":"https://orcid.org/0000-0001-9220-4294"},"institutions":[{"id":"https://openalex.org/I4210100258","display_name":"National Confidential Enquiry into Patient Outcome and Death","ror":"https://ror.org/016knsn07","country_code":"GB","type":"nonprofit","lineage":["https://openalex.org/I4210100258"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Qingbing Ji","raw_affiliation_strings":["Key Laboratories for Confidential Communications, Thirtieth Research Institute of CETC Corporation, Chengdu, China","Key laboratories for confidential communications, Thirtieth Research Institute of CETC Corporation, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0001-9220-4294","affiliations":[{"raw_affiliation_string":"Key Laboratories for Confidential Communications, Thirtieth Research Institute of CETC Corporation, Chengdu, China","institution_ids":["https://openalex.org/I4210100258"]},{"raw_affiliation_string":"Key laboratories for confidential communications, Thirtieth Research Institute of CETC Corporation, Chengdu, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061189209","display_name":"Kao\u2010Shing Hwang","orcid":"https://orcid.org/0000-0001-9234-4836"},"institutions":[{"id":"https://openalex.org/I142974352","display_name":"National Sun Yat-sen University","ror":"https://ror.org/00mjawt10","country_code":"TW","type":"education","lineage":["https://openalex.org/I142974352"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Kao-Shing Hwang","raw_affiliation_strings":["Department of Electrical Engineering, National Sun Yat-sen University, Taiwan, China","Department of Electrical EngineeringNational Sun Yat-sen University"],"raw_orcid":"https://orcid.org/0000-0001-9234-4836","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, National Sun Yat-sen University, Taiwan, China","institution_ids":["https://openalex.org/I142974352"]},{"raw_affiliation_string":"Department of Electrical EngineeringNational Sun Yat-sen University","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101502589","display_name":"Xianshan Li","orcid":"https://orcid.org/0000-0003-0101-3973"},"institutions":[{"id":"https://openalex.org/I39333907","display_name":"Yanshan University","ror":"https://ror.org/02txfnf15","country_code":"CN","type":"education","lineage":["https://openalex.org/I39333907"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xianshan Li","raw_affiliation_strings":["School of Information Science and Engineering, Yanshan University, Qinghuangdao, China"],"raw_orcid":"https://orcid.org/0000-0003-0101-3973","affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Yanshan University, Qinghuangdao, China","institution_ids":["https://openalex.org/I39333907"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.12614877,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"17","issue":"2","first_page":"379","last_page":"389"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.8476999998092651,"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":0.8476999998092651,"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/T11252","display_name":"Evolutionary Game Theory and Cooperation","score":0.7376000285148621,"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/computer-science","display_name":"Computer science","score":0.8302592039108276},{"id":"https://openalex.org/keywords/curiosity","display_name":"Curiosity","score":0.8060177564620972},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7450726628303528},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.5074030756950378},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4266171455383301},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.42164042592048645},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.07191327214241028},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.0645689070224762}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8302592039108276},{"id":"https://openalex.org/C33435437","wikidata":"https://www.wikidata.org/wiki/Q366791","display_name":"Curiosity","level":2,"score":0.8060177564620972},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7450726628303528},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5074030756950378},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4266171455383301},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.42164042592048645},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.07191327214241028},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0645689070224762}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcds.2024.3460368","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcds.2024.3460368","pdf_url":null,"source":{"id":"https://openalex.org/S2488537894","display_name":"IEEE Transactions on Cognitive and Developmental Systems","issn_l":"2379-8920","issn":["2379-8920","2379-8939"],"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 Cognitive and Developmental Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1586735782","display_name":null,"funder_award_id":"62476225","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8274292341","display_name":null,"funder_award_id":"62076202","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W2012812921","https://openalex.org/W2088956500","https://openalex.org/W2588790649","https://openalex.org/W2747213132","https://openalex.org/W2963523627","https://openalex.org/W2978069508","https://openalex.org/W2997070234","https://openalex.org/W2997289589","https://openalex.org/W3081661003","https://openalex.org/W3134527491","https://openalex.org/W3145193500","https://openalex.org/W3175552386","https://openalex.org/W3181648466","https://openalex.org/W3198359393","https://openalex.org/W4289820419","https://openalex.org/W4379409346","https://openalex.org/W4387681925","https://openalex.org/W4388081402","https://openalex.org/W4389459425","https://openalex.org/W4389542939","https://openalex.org/W4389747922","https://openalex.org/W6716474083","https://openalex.org/W6730641667","https://openalex.org/W6735033012","https://openalex.org/W6739516088","https://openalex.org/W6747941106","https://openalex.org/W6748603076","https://openalex.org/W6749304979","https://openalex.org/W6751139674","https://openalex.org/W6754957883","https://openalex.org/W6756303580","https://openalex.org/W6758763022","https://openalex.org/W6758846586","https://openalex.org/W6762491519","https://openalex.org/W6764724164","https://openalex.org/W6767327128","https://openalex.org/W6768539364","https://openalex.org/W6769462197","https://openalex.org/W6773447848","https://openalex.org/W6778000925","https://openalex.org/W6781750019","https://openalex.org/W6791194670","https://openalex.org/W6796667233","https://openalex.org/W6796991022","https://openalex.org/W6797416203","https://openalex.org/W6803709789","https://openalex.org/W6842398486","https://openalex.org/W6843745752","https://openalex.org/W6846255677","https://openalex.org/W6852461623","https://openalex.org/W6856876844","https://openalex.org/W6858079367","https://openalex.org/W6868586910","https://openalex.org/W6868825112","https://openalex.org/W7000508211"],"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":{"Efficient":[0],"exploration":[1,22,26,154],"in":[2,10,47,106,125,156],"cooperative":[3,143],"multiagent":[4,20,126],"reinforcement":[5],"learning":[6],"is":[7],"still":[8],"tricky":[9],"complex":[11],"tasks.":[12],"In":[13,110],"this":[14],"article,":[15],"we":[16,42,76],"propose":[17],"a":[18,53,159],"novel":[19,35,94],"collaborative":[21,153],"method":[23],"called":[24],"neighborhood-curiosity-based":[25],"(NCE),":[27],"by":[28,116],"which":[29],"agents":[30,92,112,131,137],"can":[31,64,135,150],"explore":[32],"not":[33],"only":[34,120],"states":[36,95],"but":[37],"also":[38],"new":[39,97],"partnerships.":[40],"Concretely,":[41],"use":[43,77],"the":[44,71,78,82,140,175],"attention":[45,62],"mechanism":[46],"graph":[48],"convolutional":[49],"networks":[50],"to":[51,88,138],"perform":[52],"weighted":[54],"summation":[55],"of":[56,70,81,162],"features":[57,84],"from":[58],"neighbors.":[59],"The":[60],"calculated":[61],"weights":[63],"be":[65],"regarded":[66],"as":[67,85],"an":[68],"embodiment":[69],"relationship":[72],"among":[73],"agents.":[74,147,163],"Then,":[75],"prediction":[79,103],"errors":[80],"aggregated":[83],"intrinsic":[86,108],"rewards":[87],"facilitate":[89],"exploration.":[90],"When":[91],"encounter":[93],"or":[96],"partnerships,":[98],"NCE":[99,149,169],"will":[100],"produce":[101],"large":[102,107,160],"errors,":[104],"resulting":[105],"rewards.":[109],"addition,":[111],"are":[113],"more":[114],"influenced":[115],"their":[117,133],"neighbors":[118,134],"and":[119,132],"interact":[121],"directly":[122],"with":[123,145,158],"them":[124],"systems.":[127],"Exploring":[128],"partnerships":[129],"between":[130],"enable":[136],"capture":[139],"most":[141],"important":[142],"relations":[144],"other":[146],"Therefore,":[148],"effectively":[151],"promote":[152],"even":[155],"environments":[157],"number":[161],"Our":[164],"experimental":[165],"results":[166],"show":[167],"that":[168],"achieves":[170],"significant":[171],"performance":[172],"improvements":[173],"on":[174],"challenging":[176],"StarCraft":[177],"II":[178],"micromanagement":[179],"(SMAC)":[180],"benchmark.":[181]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}