{"id":"https://openalex.org/W4413406546","doi":"https://doi.org/10.1016/j.icte.2025.07.010","title":"Learning graph based individual intrinsic reward for multi-agent reinforcement learning","display_name":"Learning graph based individual intrinsic reward for multi-agent reinforcement learning","publication_year":2025,"publication_date":"2025-08-21","ids":{"openalex":"https://openalex.org/W4413406546","doi":"https://doi.org/10.1016/j.icte.2025.07.010"},"language":"en","primary_location":{"id":"doi:10.1016/j.icte.2025.07.010","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.icte.2025.07.010","pdf_url":null,"source":{"id":"https://openalex.org/S2898368220","display_name":"ICT Express","issn_l":"2405-9595","issn":["2405-9595"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICT Express","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1016/j.icte.2025.07.010","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113319843","display_name":"Seokhun Ju","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seokhun Ju","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Seoul National University, Seoul, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004018143","display_name":"Seungyub Han","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seungyub Han","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Seoul National University, Seoul, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029760359","display_name":"Taehyun Cho","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Taehyun Cho","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Seoul National University, Seoul, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100376261","display_name":"Jungwoo Lee","orcid":"https://orcid.org/0000-0002-6804-980X"},"institutions":[{"id":"https://openalex.org/I4210143937","display_name":"Hanwha Solutions (South Korea)","ror":"https://ror.org/05dmq6f22","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210143937","https://openalex.org/I4403386467"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Jungwoo Lee","raw_affiliation_strings":["Intelligent SW team, Hanwha System, Seongnam, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-6804-980X","affiliations":[{"raw_affiliation_string":"Intelligent SW team, Hanwha System, Seongnam, South Korea","institution_ids":["https://openalex.org/I4210143937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020132536","display_name":"Taeyoung Lee","orcid":"https://orcid.org/0000-0003-4982-4150"},"institutions":[{"id":"https://openalex.org/I4210143937","display_name":"Hanwha Solutions (South Korea)","ror":"https://ror.org/05dmq6f22","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210143937","https://openalex.org/I4403386467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Taeyoung Lee","raw_affiliation_strings":["Intelligent SW team, Hanwha System, Seongnam, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligent SW team, Hanwha System, Seongnam, South Korea","institution_ids":["https://openalex.org/I4210143937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111275079","display_name":"Minkyoung Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I4210143937","display_name":"Hanwha Solutions (South Korea)","ror":"https://ror.org/05dmq6f22","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210143937","https://openalex.org/I4403386467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Minkyoung Kim","raw_affiliation_strings":["Intelligent SW team, Hanwha System, Seongnam, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligent SW team, Hanwha System, Seongnam, South Korea","institution_ids":["https://openalex.org/I4210143937"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017309732","display_name":"Jinung An","orcid":"https://orcid.org/0000-0001-9041-3201"},"institutions":[{"id":"https://openalex.org/I4210143937","display_name":"Hanwha Solutions (South Korea)","ror":"https://ror.org/05dmq6f22","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210143937","https://openalex.org/I4403386467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jinho An","raw_affiliation_strings":["Intelligent SW team, Hanwha System, Seongnam, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligent SW team, Hanwha System, Seongnam, South Korea","institution_ids":["https://openalex.org/I4210143937"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100376261"],"corresponding_institution_ids":["https://openalex.org/I4210143937"],"apc_list":{"value":1500,"currency":"USD","value_usd":1500},"apc_paid":{"value":1500,"currency":"USD","value_usd":1500},"fwci":1.396,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.85508518,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"12","issue":"2","first_page":"301","last_page":"305"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9596999883651733,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9556000232696533,"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":0.6690578460693359},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.6439592838287354},{"id":"https://openalex.org/keywords/intrinsic-motivation","display_name":"Intrinsic motivation","score":0.49578842520713806},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.4889289438724518},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4795117676258087},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.4478894770145416},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.3675340712070465},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.36624613404273987},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35236412286758423},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.23960727453231812}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6690578460693359},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.6439592838287354},{"id":"https://openalex.org/C2985564149","wikidata":"https://www.wikidata.org/wiki/Q644302","display_name":"Intrinsic motivation","level":2,"score":0.49578842520713806},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.4889289438724518},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4795117676258087},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.4478894770145416},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3675340712070465},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.36624613404273987},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35236412286758423},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.23960727453231812}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1016/j.icte.2025.07.010","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.icte.2025.07.010","pdf_url":null,"source":{"id":"https://openalex.org/S2898368220","display_name":"ICT Express","issn_l":"2405-9595","issn":["2405-9595"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICT Express","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:879394205e064966a4a89964b6b00a27","is_oa":true,"landing_page_url":"https://doaj.org/article/879394205e064966a4a89964b6b00a27","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":"ICT Express, Vol 12, Iss 2, Pp 301-305 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1016/j.icte.2025.07.010","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.icte.2025.07.010","pdf_url":null,"source":{"id":"https://openalex.org/S2898368220","display_name":"ICT Express","issn_l":"2405-9595","issn":["2405-9595"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICT Express","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.4699999988079071,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1501856433","https://openalex.org/W2088956500","https://openalex.org/W2145339207","https://openalex.org/W2257979135","https://openalex.org/W2617547828","https://openalex.org/W2963762747","https://openalex.org/W2970272688","https://openalex.org/W2982316857","https://openalex.org/W3197299742","https://openalex.org/W4385245566","https://openalex.org/W4393176181","https://openalex.org/W6630044934","https://openalex.org/W6737849119","https://openalex.org/W6739901393","https://openalex.org/W6766805167","https://openalex.org/W6767151588","https://openalex.org/W6840199509"],"related_works":["https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588","https://openalex.org/W2086122291","https://openalex.org/W1987513656"],"abstract_inverted_index":{"Designing":[0],"a":[1,5,23,82,97,125,157],"reward":[2,24,46,61,85,100,130,160],"function":[3,25,86,101],"is":[4,69,102],"critical":[6],"challenge":[7,68],"in":[8,108],"reinforcement":[9,39,65,106,149],"learning.":[10,121],"However,":[11],"as":[12],"environments":[13],"become":[14],"more":[15,20,88],"complex":[16,75],"and":[17,147],"tasks":[18],"grow":[19],"difficult,":[21],"designing":[22,81],"that":[26,44,95,132],"drives":[27],"optimal":[28,119,139],"behavior":[29],"becomes":[30],"increasingly":[31],"challenging.":[32],"To":[33],"overcome":[34],"these":[35],"issues,":[36],"Preference":[37],"based":[38,48,154],"learning":[40,107,128,156],"has":[41],"proposed":[42],"methods":[43],"learn":[45],"functions":[47,131],"on":[49,155],"the":[50,57,67,74,152],"preference":[51],"between":[52],"two":[53],"trajectories,":[54],"thereby":[55],"eliminating":[56],"need":[58],"for":[59,118,127,136],"handcrafted":[60],"function.":[62,161],"In":[63,90],"multi-agent":[64,109],"learning,":[66,150],"even":[70,87],"greater":[71],"due":[72],"to":[73,114],"interactions":[76],"among":[77],"agents,":[78],"which":[79,143],"makes":[80],"single":[83,98],"global":[84,99,159],"difficult.":[89],"this":[91],"paper,":[92],"we":[93,123],"show":[94],"when":[96],"learned":[103],"via":[104],"preference-based":[105,148],"setting,":[110],"it":[111],"often":[112],"fails":[113],"capture":[115],"sufficient":[116],"information":[117],"policy":[120],"Instead,":[122],"propose":[124],"method":[126,153],"individual":[129],"provide":[133],"additional":[134],"guidance":[135],"each":[137],"agent\u2019s":[138],"policy.":[140],"Our":[141],"approach,":[142],"leverages":[144],"graph":[145],"structures":[146],"outperforms":[151],"single,":[158]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-14T06:11:07.267592","created_date":"2025-10-10T00:00:00"}