{"id":"https://openalex.org/W3007999377","doi":"https://doi.org/10.1109/redundancy48165.2019.9003345","title":"MAGNet: Multi-agent Graph Network for Deep Multi-agent Reinforcement Learning","display_name":"MAGNet: Multi-agent Graph Network for Deep Multi-agent Reinforcement Learning","publication_year":2019,"publication_date":"2019-10-01","ids":{"openalex":"https://openalex.org/W3007999377","doi":"https://doi.org/10.1109/redundancy48165.2019.9003345","mag":"3007999377"},"language":"en","primary_location":{"id":"doi:10.1109/redundancy48165.2019.9003345","is_oa":false,"landing_page_url":"https://doi.org/10.1109/redundancy48165.2019.9003345","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 XVI International Symposium \"Problems of Redundancy in Information and Control Systems\" (REDUNDANCY)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2012.09762","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Aleksandra Malysheva","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Aleksandra Malysheva","raw_affiliation_strings":["JetBrains Research, National Research University, St Petersburg, Russia"],"affiliations":[{"raw_affiliation_string":"JetBrains Research, National Research University, St Petersburg, Russia","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Daniel Kudenko","orcid":null},"institutions":[{"id":"https://openalex.org/I114112103","display_name":"Leibniz University Hannover","ror":"https://ror.org/0304hq317","country_code":"DE","type":"education","lineage":["https://openalex.org/I114112103"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Daniel Kudenko","raw_affiliation_strings":["JetBrains Research, Leibniz University Hannover, Hannover, Germany"],"affiliations":[{"raw_affiliation_string":"JetBrains Research, Leibniz University Hannover, Hannover, Germany","institution_ids":["https://openalex.org/I114112103"]}]},{"author_position":"last","author":{"id":null,"display_name":"Aleksei Shpilman","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aleksei Shpilman","raw_affiliation_strings":["JetBrains Research, National Research University, St Petersburg, Russia"],"affiliations":[{"raw_affiliation_string":"JetBrains Research, National Research University, St Petersburg, Russia","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.302,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.86158991,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"171","last_page":"176"},"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.9767000079154968,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.97079998254776,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8205999732017517},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5220000147819519},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.48410001397132874},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.3993000090122223},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.39500001072883606},{"id":"https://openalex.org/keywords/learning-classifier-system","display_name":"Learning classifier system","score":0.3441999852657318}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8205999732017517},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.667900025844574},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6672000288963318},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5220000147819519},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.48410001397132874},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.3993000090122223},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.39500001072883606},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36070001125335693},{"id":"https://openalex.org/C199190896","wikidata":"https://www.wikidata.org/wiki/Q3509276","display_name":"Learning classifier system","level":3,"score":0.3441999852657318},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.31779998540878296},{"id":"https://openalex.org/C146380142","wikidata":"https://www.wikidata.org/wiki/Q1137726","display_name":"Directed graph","level":2,"score":0.29249998927116394},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2906999886035919},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.2540999948978424}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/redundancy48165.2019.9003345","is_oa":false,"landing_page_url":"https://doi.org/10.1109/redundancy48165.2019.9003345","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 XVI International Symposium \"Problems of Redundancy in Information and Control Systems\" (REDUNDANCY)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2012.09762","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2012.09762","pdf_url":"https://arxiv.org/pdf/2012.09762","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2012.09762","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2012.09762","pdf_url":"https://arxiv.org/pdf/2012.09762","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2602275733","https://openalex.org/W6637967152","https://openalex.org/W6638667902","https://openalex.org/W6638824847","https://openalex.org/W6683204974","https://openalex.org/W6684921986","https://openalex.org/W6738796088","https://openalex.org/W6739901393","https://openalex.org/W6749304979"],"related_works":[],"abstract_inverted_index":{"Over":[0],"recent":[1],"years,":[2],"deep":[3],"reinforcement":[4,38],"learning":[5,39],"has":[6,19],"shown":[7],"strong":[8],"successes":[9],"in":[10],"complex":[11],"single-agent":[12],"tasks,":[13],"and":[14,54,69,73,95],"more":[15],"recently":[16],"this":[17,27],"approach":[18,62],"also":[20],"been":[21],"applied":[22,59],"to":[23,36,63],"multi-agent":[24,37,67],"domains.":[25],"In":[26],"paper,":[28],"we":[29],"propose":[30],"a":[31,42,51,55],"novel":[32],"approach,":[33],"called":[34],"MAGNet,":[35],"that":[40,77],"utilizes":[41],"relevance":[43],"graph":[44],"representation":[45],"of":[46],"the":[47,64,70,74],"environment":[48,68],"obtained":[49],"by":[50],"self-attention":[52],"mechanism,":[53],"message-generation":[56],"technique.":[57],"We":[58],"our":[60],"MAGnet":[61],"synthetic":[65],"predator-prey":[66],"Pommerman":[71],"game":[72],"results":[75],"show":[76],"it":[78],"significantly":[79],"outperforms":[80],"state-of-the-art":[81],"MARL":[82],"solutions,":[83],"including":[84],"Multi-agent":[85,89],"Deep":[86,90],"Q-Networks":[87],"(MADQN),":[88],"Deterministic":[91],"Policy":[92],"Gradient":[93],"(MADDPG),":[94],"QMIX.":[96]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":4}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2020-03-06T00:00:00"}