{"id":"https://openalex.org/W7198633848","doi":null,"title":"Cooperative AI Using Multi-Agent Reinforcement Learning for Team-Based Game","display_name":"Cooperative AI Using Multi-Agent Reinforcement Learning for Team-Based Game","publication_year":2026,"publication_date":"2026-04-14","ids":{"openalex":"https://openalex.org/W7198633848"},"language":"en","primary_location":{"id":"pmh:oai:dea.lib.unideb.hu:2437/413226","doi":null,"is_oa":false,"landing_page_url":"https://hdl.handle.net/2437/413226","pdf_url":null,"source":{"id":"https://openalex.org/S4306402089","display_name":"University of Debrecen Electronic Archive (University of Debrecen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I132735039","host_organization_name":"University of Debrecen","host_organization_lineage":["https://openalex.org/I132735039"],"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":null},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5145343158","display_name":"Htin Zaw Lwin Saw","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Saw, Htin Zaw Lwin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5145343158"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9980000257492065,"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":0.9980000257492065,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.0017999999690800905,"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/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.0,"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/multi-agent-reinforcement-learning","display_name":"multi-agent reinforcement learning","score":0.9879999756813049},{"id":"https://openalex.org/keywords/cooperative-behavior","display_name":"cooperative behavior","score":0.8029999732971191},{"id":"https://openalex.org/keywords/team-based-games","display_name":"team-based games","score":0.9539999961853027},{"id":"https://openalex.org/keywords/capture-the-flag","display_name":"Capture the Flag","score":0.9350000023841858},{"id":"https://openalex.org/keywords/decentralized-learning","display_name":"decentralized learning","score":0.718999981880188},{"id":"https://openalex.org/keywords/weight-sharing","display_name":"parameter sharing","score":0.7200000286102295},{"id":"https://openalex.org/keywords/role-differentiation","display_name":"role differentiation","score":0.7459999918937683},{"id":"https://openalex.org/keywords/partially-observable-environments","display_name":"partially observable environments","score":0.781000018119812},{"id":"https://openalex.org/keywords/unity-ml-agents","display_name":"Unity ML-Agents","score":0.9210000038146973}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8159000277519226},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6769000291824341},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5703999996185303},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48980000615119934},{"id":"https://openalex.org/C47932503","wikidata":"https://www.wikidata.org/wiki/Q5395689","display_name":"Error-driven learning","level":3,"score":0.4278999865055084},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.37220001220703125},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.358599990606308},{"id":"https://openalex.org/C177142836","wikidata":"https://www.wikidata.org/wiki/Q44455","display_name":"Game theory","level":2,"score":0.34310001134872437},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.3206999897956848},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3206000030040741},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.3093000054359436},{"id":"https://openalex.org/C205875254","wikidata":"https://www.wikidata.org/wiki/Q17156857","display_name":"Decentralised system","level":3,"score":0.3073999881744385},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.2996000051498413},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.2944999933242798},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.29319998621940613},{"id":"https://openalex.org/C73795354","wikidata":"https://www.wikidata.org/wiki/Q287618","display_name":"Sequential game","level":3,"score":0.2928999960422516},{"id":"https://openalex.org/C202556891","wikidata":"https://www.wikidata.org/wiki/Q1584646","display_name":"Repeated game","level":3,"score":0.28850001096725464},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.28360000252723694},{"id":"https://openalex.org/C47175762","wikidata":"https://www.wikidata.org/wiki/Q13422573","display_name":"Non-cooperative game","level":3,"score":0.2824999988079071},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.27639999985694885}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:dea.lib.unideb.hu:2437/413226","doi":null,"is_oa":false,"landing_page_url":"https://hdl.handle.net/2437/413226","pdf_url":null,"source":{"id":"https://openalex.org/S4306402089","display_name":"University of Debrecen Electronic Archive (University of Debrecen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I132735039","host_organization_name":"University of Debrecen","host_organization_lineage":["https://openalex.org/I132735039"],"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":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7029483213","https://openalex.org/W7009019420","https://openalex.org/W7084153837","https://openalex.org/W4415802035","https://openalex.org/W4391439043","https://openalex.org/W7067343410","https://openalex.org/W4416250381","https://openalex.org/W3212648065","https://openalex.org/W4412924613","https://openalex.org/W7214423912"],"abstract_inverted_index":{"This":[0],"thesis":[1],"explores":[2],"the":[3,84],"use":[4],"of":[5,86],"Multi-Agent":[6],"Reinforcement":[7],"Learning":[8],"(MARL)":[9],"to":[10,31,51],"develop":[11,69],"cooperative":[12],"behavior":[13],"in":[14,24,92],"a":[15,40,53],"team-based":[16],"game":[17],"environment.":[18],"A":[19],"capture-the-flag":[20],"scenario":[21],"is":[22],"implemented":[23],"Unity":[25],"ML-Agents,":[26],"where":[27],"agents":[28,50,67],"must":[29],"coordinate":[30],"attack,":[32],"defend,":[33],"and":[34,43,72],"capture":[35],"objectives.":[36],"The":[37,63],"system":[38],"uses":[39],"decentralized":[41,87],"training":[42],"execution":[44],"framework":[45],"with":[46,89],"parameter":[47],"sharing,":[48],"allowing":[49],"learn":[52],"common":[54],"policy":[55],"while":[56],"acting":[57],"independently":[58],"based":[59],"on":[60],"local":[61],"observations.":[62],"results":[64],"demonstrate":[65],"that":[66],"can":[68],"coordinated":[70],"strategies":[71],"role":[73],"differentiation":[74],"without":[75],"centralized":[76],"control":[77],"or":[78],"explicit":[79],"communication.":[80],"These":[81],"findings":[82],"highlight":[83],"effectiveness":[85],"MARL":[88],"shared":[90],"policies":[91],"complex,":[93],"partially":[94],"observable":[95],"environments.":[96]},"counts_by_year":[],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2026-08-07T00:00:00"}