{"id":"https://openalex.org/W4301323220","doi":"https://doi.org/10.1109/access.2022.3171053","title":"A Novel and Efficient Influence-Seeking Exploration in Deep Multiagent Reinforcement Learning","display_name":"A Novel and Efficient Influence-Seeking Exploration in Deep Multiagent Reinforcement Learning","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4301323220","doi":"https://doi.org/10.1109/access.2022.3171053"},"language":"en","primary_location":{"id":"doi:10.1109/access.2022.3171053","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2022.3171053","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/9668973/09764683.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/9668973/09764683.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5071461874","display_name":"Byunghyun Yoo","orcid":"https://orcid.org/0000-0003-0857-5565"},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Byunghyun Yoo","raw_affiliation_strings":["Electronics and Telecommunications Research Institute (ETRI), Daejeon, South Korea"],"raw_orcid":"https://orcid.org/0000-0003-0857-5565","affiliations":[{"raw_affiliation_string":"Electronics and Telecommunications Research Institute (ETRI), Daejeon, South Korea","institution_ids":["https://openalex.org/I142401562"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080626085","display_name":"Devarani Devi Ningombam","orcid":"https://orcid.org/0000-0002-6946-6584"},"institutions":[{"id":"https://openalex.org/I885392262","display_name":"GITAM University","ror":"https://ror.org/0440p1d37","country_code":"IN","type":"education","lineage":["https://openalex.org/I885392262"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Devarani Devi Ningombam","raw_affiliation_strings":["Department of Computer Science and Engineering, GITAM University, Visakhapatnam, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, GITAM University, Visakhapatnam, India","institution_ids":["https://openalex.org/I885392262"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085539609","display_name":"Sungwon Yi","orcid":"https://orcid.org/0000-0002-4986-9546"},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sungwon Yi","raw_affiliation_strings":["Electronics and Telecommunications Research Institute (ETRI), Daejeon, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electronics and Telecommunications Research Institute (ETRI), Daejeon, South Korea","institution_ids":["https://openalex.org/I142401562"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100330218","display_name":"Hyun Woo Kim","orcid":"https://orcid.org/0000-0003-2473-8360"},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyun Woo Kim","raw_affiliation_strings":["Electronics and Telecommunications Research Institute (ETRI), Daejeon, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electronics and Telecommunications Research Institute (ETRI), Daejeon, South Korea","institution_ids":["https://openalex.org/I142401562"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048021125","display_name":"Euisok Chung","orcid":"https://orcid.org/0000-0001-5091-2508"},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Euisok Chung","raw_affiliation_strings":["Electronics and Telecommunications Research Institute (ETRI), Daejeon, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electronics and Telecommunications Research Institute (ETRI), Daejeon, South Korea","institution_ids":["https://openalex.org/I142401562"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070886624","display_name":"Ran Han","orcid":"https://orcid.org/0000-0002-5566-8193"},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Ran Han","raw_affiliation_strings":["Electronics and Telecommunications Research Institute (ETRI), Daejeon, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electronics and Telecommunications Research Institute (ETRI), Daejeon, South Korea","institution_ids":["https://openalex.org/I142401562"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034406505","display_name":"Hwa Jeon Song","orcid":"https://orcid.org/0000-0002-8216-4812"},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hwa Jeon Song","raw_affiliation_strings":["Electronics and Telecommunications Research Institute (ETRI), Daejeon, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-8216-4812","affiliations":[{"raw_affiliation_string":"Electronics and Telecommunications Research Institute (ETRI), Daejeon, South Korea","institution_ids":["https://openalex.org/I142401562"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.9711,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.79953812,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":"10","issue":null,"first_page":"47741","last_page":"47753"},"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9887999892234802,"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/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.9491000175476074,"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":0.8267004489898682},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6956676244735718},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.5133468508720398},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47127410769462585}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8267004489898682},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6956676244735718},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.5133468508720398},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47127410769462585}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2022.3171053","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2022.3171053","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/9668973/09764683.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:2c52b19cd0694122b162961de7740579","is_oa":true,"landing_page_url":"https://doaj.org/article/2c52b19cd0694122b162961de7740579","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 10, Pp 47741-47753 (2022)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2022.3171053","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2022.3171053","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/9668973/09764683.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1701955658","display_name":null,"funder_award_id":"22ZS1100","funder_id":"https://openalex.org/F4320322093","funder_display_name":"Electronics and Telecommunications Research Institute"},{"id":"https://openalex.org/G3591598716","display_name":null,"funder_award_id":"FA2386","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"},{"id":"https://openalex.org/G5407164105","display_name":null,"funder_award_id":"19YE1410","funder_id":"https://openalex.org/F4320322093","funder_display_name":"Electronics and Telecommunications Research Institute"},{"id":"https://openalex.org/G6753616810","display_name":null,"funder_award_id":"FA2386-19-1-4020","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"}],"funders":[{"id":"https://openalex.org/F4320322093","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10"},{"id":"https://openalex.org/F4320338279","display_name":"Air Force Office of Scientific Research","ror":"https://ror.org/011e9bt93"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4301323220.pdf","grobid_xml":"https://content.openalex.org/works/W4301323220.grobid-xml"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W2145339207","https://openalex.org/W2511088267","https://openalex.org/W2617547828","https://openalex.org/W2736601468","https://openalex.org/W2749807327","https://openalex.org/W2798511001","https://openalex.org/W2904455790","https://openalex.org/W2963523627","https://openalex.org/W2981482273","https://openalex.org/W2996037775","https://openalex.org/W2997940961","https://openalex.org/W3015873116","https://openalex.org/W3083927356","https://openalex.org/W3198965389","https://openalex.org/W4240204763","https://openalex.org/W6638018090","https://openalex.org/W6640212811","https://openalex.org/W6677939520","https://openalex.org/W6684205842","https://openalex.org/W6684921986","https://openalex.org/W6738796088","https://openalex.org/W6741002519","https://openalex.org/W6743756900","https://openalex.org/W6749304979","https://openalex.org/W6750393176","https://openalex.org/W6752380930","https://openalex.org/W6755069753","https://openalex.org/W6758846586","https://openalex.org/W6762491519","https://openalex.org/W6767327128","https://openalex.org/W6769462197","https://openalex.org/W6772005887","https://openalex.org/W6781750019","https://openalex.org/W6783055029","https://openalex.org/W6783196708","https://openalex.org/W6784152626","https://openalex.org/W6790997415","https://openalex.org/W6791043475"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4306904969","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2138720691","https://openalex.org/W2376932109"],"abstract_inverted_index":{"Although":[0],"recent":[1],"years":[2],"witnessed":[3],"notable":[4],"success":[5],"for":[6],"a":[7,70,162],"cooperative":[8],"setting":[9],"in":[10,91,104,186,192],"multi-agent":[11,63],"reinforcement":[12],"learning":[13,95],"(MARL),":[14],"efficient":[15,38],"explorations":[16],"are":[17],"still":[18],"challenging":[19],"primarily":[20],"due":[21],"to":[22,43,55,79,126,151,175],"the":[23,30,60,94,99,109,141,157,178],"complex":[24],"dynamics":[25],"of":[26,33,62,101,111,118,143,164,184],"inter-agent":[27],"interactions":[28,49],"constituting":[29],"high":[31],"dimension":[32],"action":[34,82,105,116],"spaces.":[35],"For":[36],"an":[37,123,136,152],"exploration,":[39],"it":[40,150],"is":[41],"necessary":[42],"quantify":[44],"influences":[45],"that":[46,120],"can":[47],"represent":[48],"among":[50],"agents":[51,78,103,119],"and":[52,88,147,190],"use":[53,108],"them":[54],"obtain":[56],"more":[57],"information":[58],"about":[59],"complexity":[61],"systems.":[64],"In":[65],"this":[66,131],"paper,":[67],"we":[68,107,133],"propose":[69],"novel":[71],"influence-seeking":[72],"exploration":[73,153,159],"(ISE)":[74],"scheme,":[75],"which":[76],"encourages":[77],"preferably":[80],"explore":[81],"spaces":[83],"significantly":[84],"influenced":[85],"by":[86,122,140],"others":[87],"thus":[89],"helps":[90],"speeding":[92],"up":[93],"curve.":[96],"To":[97,130],"measure":[98],"influence":[100],"other":[102],"selection,":[106],"variance":[110,145],"joint":[112],"action-values":[113],"with":[114],"different":[115],"sets":[117],"obtained":[121],"estimation":[124],"technique":[125],"lessen":[127],"computation":[128],"overhead.":[129],"end,":[132],"first":[134],"present":[135],"analytical":[137],"approach":[138],"inspired":[139],"concept":[142],"approximated":[144],"propagation":[146],"then":[148],"apply":[149],"scheme.":[154],"We":[155],"evaluate":[156],"proposed":[158,179],"method":[160,180],"on":[161],"set":[163],"StarCraft":[165,187],"II":[166,188],"micromanagement":[167,189],"as":[168,170],"well":[169],"modified":[171,193],"predator-prey":[172,194],"tasks.":[173],"Compared":[174],"state-of-the-art":[176],"methods,":[177],"achieved":[181],"performance":[182],"improvements":[183],"10%":[185],"50%":[191],"tasks":[195],"approximately.":[196]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}