{"id":"https://openalex.org/W4394627306","doi":"https://doi.org/10.1109/tnnls.2024.3382480","title":"Graph Exploration for Effective Multiagent Q-Learning","display_name":"Graph Exploration for Effective Multiagent Q-Learning","publication_year":2024,"publication_date":"2024-04-09","ids":{"openalex":"https://openalex.org/W4394627306","doi":"https://doi.org/10.1109/tnnls.2024.3382480","pmid":"https://pubmed.ncbi.nlm.nih.gov/38593017"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2024.3382480","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2024.3382480","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://infoscience.epfl.ch/handle/20.500.14299/207684","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5050066871","display_name":"Ainur Zhaikhan","orcid":"https://orcid.org/0000-0002-7240-9249"},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Ainur Zhaikhan","raw_affiliation_strings":["Adaptive Systems Laboratory, École Polytechnique Fédérale de Lausanne (EPFL), Lausanne, Switzerland"],"raw_orcid":"https://orcid.org/0000-0002-7240-9249","affiliations":[{"raw_affiliation_string":"Adaptive Systems Laboratory, École Polytechnique Fédérale de Lausanne (EPFL), Lausanne, Switzerland","institution_ids":["https://openalex.org/I5124864"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091103447","display_name":"Ali H. Sayed","orcid":"https://orcid.org/0000-0002-5125-5519"},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Ali H. Sayed","raw_affiliation_strings":["Adaptive Systems Laboratory, École Polytechnique Fédérale de Lausanne (EPFL), Lausanne, Switzerland"],"raw_orcid":"https://orcid.org/0000-0002-5125-5519","affiliations":[{"raw_affiliation_string":"Adaptive Systems Laboratory, École Polytechnique Fédérale de Lausanne (EPFL), Lausanne, Switzerland","institution_ids":["https://openalex.org/I5124864"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5050066871"],"corresponding_institution_ids":["https://openalex.org/I5124864"],"apc_list":null,"apc_paid":null,"fwci":0.9934,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.78601241,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"36","issue":"3","first_page":"5535","last_page":"5546"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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/T10603","display_name":"Smart Grid Energy Management","score":0.9955999851226807,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.988099992275238,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.744580864906311},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7393965125083923},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.6237623691558838},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.5718158483505249},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5157580375671387},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.48448559641838074},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.4608902335166931},{"id":"https://openalex.org/keywords/information-exchange","display_name":"Information exchange","score":0.4288441240787506},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3998052477836609},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.34952491521835327},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.18237203359603882},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11490201950073242}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.744580864906311},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7393965125083923},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.6237623691558838},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.5718158483505249},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5157580375671387},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.48448559641838074},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.4608902335166931},{"id":"https://openalex.org/C189693848","wikidata":"https://www.wikidata.org/wiki/Q6031064","display_name":"Information exchange","level":2,"score":0.4288441240787506},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3998052477836609},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.34952491521835327},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.18237203359603882},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11490201950073242},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tnnls.2024.3382480","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2024.3382480","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:38593017","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38593017","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":null},{"id":"pmh:oai:infoscience.epfl.ch:310821","is_oa":true,"landing_page_url":"https://infoscience.epfl.ch/handle/20.500.14299/207684","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"WoS","raw_type":"research article"}],"best_oa_location":{"id":"pmh:oai:infoscience.epfl.ch:310821","is_oa":true,"landing_page_url":"https://infoscience.epfl.ch/handle/20.500.14299/207684","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"WoS","raw_type":"research article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W2118686230","https://openalex.org/W2150147323","https://openalex.org/W2150339816","https://openalex.org/W2626637010","https://openalex.org/W2785315072","https://openalex.org/W2963762747","https://openalex.org/W2982316857","https://openalex.org/W3033236962","https://openalex.org/W3037849017","https://openalex.org/W3049644873","https://openalex.org/W3091830134","https://openalex.org/W3205806283","https://openalex.org/W4214717370","https://openalex.org/W4220747123","https://openalex.org/W4233696721","https://openalex.org/W4287017924","https://openalex.org/W4287279898","https://openalex.org/W4287322058","https://openalex.org/W4288049695","https://openalex.org/W4327640397","https://openalex.org/W4366238939","https://openalex.org/W4366609557","https://openalex.org/W4379386431","https://openalex.org/W4388240237","https://openalex.org/W6637033378","https://openalex.org/W6678494045","https://openalex.org/W6685043521","https://openalex.org/W6695011786","https://openalex.org/W6704571135","https://openalex.org/W6734678876","https://openalex.org/W6738796088","https://openalex.org/W6739516088","https://openalex.org/W6747941106","https://openalex.org/W6766805167","https://openalex.org/W6779685389","https://openalex.org/W6784152626","https://openalex.org/W6784317198","https://openalex.org/W6787472095","https://openalex.org/W6791334070","https://openalex.org/W6793092151","https://openalex.org/W6796991022","https://openalex.org/W6800089562","https://openalex.org/W6922480057"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W4225571923","https://openalex.org/W3212257828","https://openalex.org/W2999580272","https://openalex.org/W4297873223","https://openalex.org/W3009457412","https://openalex.org/W2350784623","https://openalex.org/W2126211886","https://openalex.org/W2928233854","https://openalex.org/W2889555279"],"abstract_inverted_index":{"This":[0],"article":[1],"proposes":[2],"an":[3],"exploration":[4],"technique":[5],"for":[6,105,128,134],"multiagent":[7],"reinforcement":[8],"learning":[9],"(MARL)":[10],"with":[11,100,125,132],"graph-based":[12],"communication":[13],"among":[14],"agents.":[15],"We":[16],"assume":[17],"that":[18],"the":[19,24,29,32,41,49,52,67,88,121,135],"individual":[20],"rewards":[21],"received":[22],"by":[23,31],"agents":[25,45,92],"are":[26,38],"independent":[27],"of":[28,120],"actions":[30],"other":[33],"agents,":[34],"while":[35],"their":[36],"policies":[37],"coupled.":[39],"In":[40],"proposed":[42,68,89],"framework,":[43],"neighboring":[44],"collaborate":[46],"to":[47,57,79,93,111],"estimate":[48],"uncertainty":[50],"about":[51],"state-action":[53],"space":[54],"in":[55,95],"order":[56],"execute":[58],"more":[59],"efficient":[60],"explorative":[61],"behavior.":[62],"Different":[63],"from":[64],"existing":[65],"works,":[66],"algorithm":[69,122],"does":[70],"not":[71],"require":[72],"counting":[73],"mechanisms":[74],"and":[75,131],"can":[76],"be":[77],"applied":[78],"continuous-state":[80,106],"environments":[81],"without":[82],"requiring":[83],"complex":[84],"conversion":[85],"techniques.":[86],"Moreover,":[87],"scheme":[90],"allows":[91],"communicate":[94],"a":[96,114],"fully":[97],"decentralized":[98],"manner":[99],"minimal":[101],"information":[102],"exchange.":[103],"And":[104],"scenarios,":[107],"each":[108],"agent":[109],"needs":[110],"exchange":[112],"only":[113],"single":[115],"parameter":[116],"vector.":[117],"The":[118],"performance":[119],"is":[123],"verified":[124],"theoretical":[126],"results":[127],"discrete-state":[129],"scenarios":[130],"experiments":[133],"continuous":[136],"ones.":[137]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}