{"id":"https://openalex.org/W3014001968","doi":"https://doi.org/10.1109/ijcnn48605.2020.9206879","title":"Multi-Agent Reinforcement Learning for Problems with Combined Individual and Team Reward","display_name":"Multi-Agent Reinforcement Learning for Problems with Combined Individual and Team Reward","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3014001968","doi":"https://doi.org/10.1109/ijcnn48605.2020.9206879","mag":"3014001968"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn48605.2020.9206879","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn48605.2020.9206879","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2003.10598","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002510185","display_name":"Hassam Ullah Sheikh","orcid":null},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hassam Ullah Sheikh","raw_affiliation_strings":["Department of Computer Science, University of Central Florida, Orlando, USA","University of central florida"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Central Florida, Orlando, USA","institution_ids":["https://openalex.org/I106165777"]},{"raw_affiliation_string":"University of central florida","institution_ids":["https://openalex.org/I106165777"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042166639","display_name":"Ladislau B\u00f6l\u00f6ni","orcid":"https://orcid.org/0000-0001-5336-9651"},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ladislau Boloni","raw_affiliation_strings":["Department of Computer Science, University of Central Florida, Orlando, USA","University of central florida"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Central Florida, Orlando, USA","institution_ids":["https://openalex.org/I106165777"]},{"raw_affiliation_string":"University of central florida","institution_ids":["https://openalex.org/I106165777"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5002510185"],"corresponding_institution_ids":["https://openalex.org/I106165777"],"apc_list":null,"apc_paid":null,"fwci":0.2743,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.62576226,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"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":0.9962999820709229,"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9865999817848206,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.895789623260498},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6711564064025879},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6615245342254639},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6137760877609253},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5698224902153015},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.534991443157196},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3530294895172119},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1398443877696991},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11307820677757263},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.09105125069618225}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.895789623260498},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6711564064025879},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6615245342254639},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6137760877609253},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5698224902153015},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.534991443157196},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3530294895172119},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1398443877696991},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11307820677757263},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.09105125069618225},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/ijcnn48605.2020.9206879","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn48605.2020.9206879","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2003.10598","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2003.10598","pdf_url":"https://arxiv.org/pdf/2003.10598","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"},{"id":"mag:3014001968","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2003.10598.pdf","pdf_url":null,"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2003.10598","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2003.10598","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2003.10598","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2003.10598","pdf_url":"https://arxiv.org/pdf/2003.10598","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":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3014001968.pdf","grobid_xml":"https://content.openalex.org/works/W3014001968.grobid-xml"},"referenced_works_count":50,"referenced_works":["https://openalex.org/W1542941925","https://openalex.org/W1641379095","https://openalex.org/W2012812921","https://openalex.org/W2015410655","https://openalex.org/W2107544712","https://openalex.org/W2120846115","https://openalex.org/W2155968351","https://openalex.org/W2165150801","https://openalex.org/W2258882655","https://openalex.org/W2594829461","https://openalex.org/W2604873668","https://openalex.org/W2617547828","https://openalex.org/W2736601468","https://openalex.org/W2746553466","https://openalex.org/W2810602713","https://openalex.org/W2890509590","https://openalex.org/W2911852647","https://openalex.org/W2961255096","https://openalex.org/W2962938168","https://openalex.org/W2963477884","https://openalex.org/W2963650250","https://openalex.org/W2963747324","https://openalex.org/W2963864421","https://openalex.org/W2963881016","https://openalex.org/W2963923407","https://openalex.org/W2973525135","https://openalex.org/W2978148161","https://openalex.org/W2982316857","https://openalex.org/W2995874959","https://openalex.org/W3093287223","https://openalex.org/W6678168664","https://openalex.org/W6684205842","https://openalex.org/W6684921986","https://openalex.org/W6687681856","https://openalex.org/W6734215269","https://openalex.org/W6735011893","https://openalex.org/W6735650757","https://openalex.org/W6736572398","https://openalex.org/W6738796088","https://openalex.org/W6741002519","https://openalex.org/W6747993910","https://openalex.org/W6748839928","https://openalex.org/W6749032143","https://openalex.org/W6749304979","https://openalex.org/W6754689381","https://openalex.org/W6754832959","https://openalex.org/W6758367636","https://openalex.org/W6767919266","https://openalex.org/W6768731700","https://openalex.org/W6947956204"],"related_works":["https://openalex.org/W2152050309","https://openalex.org/W2014394432","https://openalex.org/W3199299551","https://openalex.org/W3081792789","https://openalex.org/W2952465248","https://openalex.org/W2807741983","https://openalex.org/W3091147964","https://openalex.org/W2393520302","https://openalex.org/W3089491416","https://openalex.org/W3038835214","https://openalex.org/W2997372031","https://openalex.org/W2550770153","https://openalex.org/W3208966735","https://openalex.org/W2897200624","https://openalex.org/W2964096423","https://openalex.org/W1972847450","https://openalex.org/W3092203123","https://openalex.org/W2470626288","https://openalex.org/W2787193614","https://openalex.org/W2408295367"],"abstract_inverted_index":{"Many":[0],"cooperative":[1,77],"multi-agent":[2,27,78],"problems":[3],"require":[4],"agents":[5],"to":[6,12,33,59,85],"learn":[7],"individual":[8,44],"tasks":[9],"while":[10],"contributing":[11],"the":[13,17,36,40,43,54,87,97,114,118],"collective":[14],"success":[15],"of":[16,39,53,117],"group.":[18],"This":[19],"is":[20,49,56],"a":[21,75],"challenging":[22],"task":[23],"for":[24],"current":[25],"state-of-the-art":[26],"reinforcement":[28,79],"algorithms":[29],"that":[30,82,104],"are":[31],"designed":[32],"maximize":[34,86],"either":[35,52],"global":[37,88],"reward":[38],"team":[41,100],"or":[42],"local":[45,90],"rewards.":[46,91],"The":[47],"problem":[48,101],"exacerbated":[50],"when":[51],"rewards":[55],"sparse":[57],"leading":[58],"unstable":[60],"learning.":[61],"To":[62],"address":[63],"this":[64],"problem,":[65],"we":[66],"present":[67],"Decomposed":[68],"Multi-Agent":[69],"Deep":[70],"Deterministic":[71],"Policy":[72],"Gradient":[73],"(DE-MADDPG):":[74],"novel":[76],"learning":[80],"framework":[81],"simultaneously":[83],"learns":[84],"and":[89,102,109],"We":[92],"evaluate":[93],"our":[94,105],"solution":[95,106],"on":[96],"defensive":[98],"escort":[99],"show":[103],"achieves":[107],"better":[108],"more":[110],"stable":[111],"performance":[112],"than":[113],"direct":[115],"adaptation":[116],"MADDPG":[119],"algorithm.":[120]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":2}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}