{"id":"https://openalex.org/W4388145791","doi":"https://doi.org/10.1109/tg.2023.3329376","title":"MDDP: Making Decisions From Different Perspectives in Multiagent Reinforcement Learning","display_name":"MDDP: Making Decisions From Different Perspectives in Multiagent Reinforcement Learning","publication_year":2023,"publication_date":"2023-11-01","ids":{"openalex":"https://openalex.org/W4388145791","doi":"https://doi.org/10.1109/tg.2023.3329376"},"language":"en","primary_location":{"id":"doi:10.1109/tg.2023.3329376","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/tg.2023.3329376","pdf_url":null,"source":{"id":"https://openalex.org/S4210224842","display_name":"IEEE Transactions on Games","issn_l":"2475-1502","issn":["2475-1502","2475-1510"],"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 Games","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"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/A5100318314","display_name":"Wei Li","orcid":"https://orcid.org/0000-0002-9235-9429"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wei Li","raw_affiliation_strings":["School of Instrument Science and Engineering, Southeast University, Nanjing, China","School of Instrument Science and Engineering, Southeast University, Nanjing, Jiangsu, China"],"raw_orcid":"https://orcid.org/0000-0002-9235-9429","affiliations":[{"raw_affiliation_string":"School of Instrument Science and Engineering, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]},{"raw_affiliation_string":"School of Instrument Science and Engineering, Southeast University, Nanjing, Jiangsu, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101858605","display_name":"Ziming Qiu","orcid":"https://orcid.org/0000-0002-7287-5936"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziming Qiu","raw_affiliation_strings":["School of Instrument Science and Engineering, Southeast University, Nanjing, China","School of Instrument Science and Engineering, Southeast University, Nanjing, Jiangsu, China"],"raw_orcid":"https://orcid.org/0000-0002-7287-5936","affiliations":[{"raw_affiliation_string":"School of Instrument Science and Engineering, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]},{"raw_affiliation_string":"School of Instrument Science and Engineering, Southeast University, Nanjing, Jiangsu, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073038991","display_name":"Shitong Shao","orcid":"https://orcid.org/0000-0003-4689-6140"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shitong Shao","raw_affiliation_strings":["School of Instrument Science and Engineering, Southeast University, Nanjing, China","School of Instrument Science and Engineering, Southeast University, Nanjing, Jiangsu, China"],"raw_orcid":"https://orcid.org/0000-0003-4689-6140","affiliations":[{"raw_affiliation_string":"School of Instrument Science and Engineering, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]},{"raw_affiliation_string":"School of Instrument Science and Engineering, Southeast University, Nanjing, Jiangsu, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048327458","display_name":"Aiguo Song","orcid":"https://orcid.org/0000-0002-1982-6780"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Aiguo Song","raw_affiliation_strings":["School of Instrument Science and Engineering, Southeast University, Nanjing, China","School of Instrument Science and Engineering, Southeast University, Nanjing, Jiangsu, China"],"raw_orcid":"https://orcid.org/0000-0002-1982-6780","affiliations":[{"raw_affiliation_string":"School of Instrument Science and Engineering, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]},{"raw_affiliation_string":"School of Instrument Science and Engineering, Southeast University, Nanjing, Jiangsu, China","institution_ids":["https://openalex.org/I76569877"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100318314"],"corresponding_institution_ids":["https://openalex.org/I76569877"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.14332176,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"16","issue":"3","first_page":"621","last_page":"634"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9302999973297119,"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":0.9302999973297119,"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":0.9069234132766724},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.7334280014038086},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7111952900886536},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6795987486839294},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.618040919303894},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5161696076393127},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.5097810626029968},{"id":"https://openalex.org/keywords/adaptability","display_name":"Adaptability","score":0.5050328373908997},{"id":"https://openalex.org/keywords/value-network","display_name":"Value network","score":0.45459699630737305},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.45086508989334106},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.4209398627281189},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12697246670722961},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10257408022880554},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.08706739544868469},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.08237713575363159}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9069234132766724},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.7334280014038086},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7111952900886536},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6795987486839294},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.618040919303894},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5161696076393127},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.5097810626029968},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.5050328373908997},{"id":"https://openalex.org/C89249532","wikidata":"https://www.wikidata.org/wiki/Q7912758","display_name":"Value network","level":3,"score":0.45459699630737305},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45086508989334106},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.4209398627281189},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12697246670722961},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10257408022880554},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.08706739544868469},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.08237713575363159},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C4216890","wikidata":"https://www.wikidata.org/wiki/Q815823","display_name":"Business model","level":2,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tg.2023.3329376","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/tg.2023.3329376","pdf_url":null,"source":{"id":"https://openalex.org/S4210224842","display_name":"IEEE Transactions on Games","issn_l":"2475-1502","issn":["2475-1502","2475-1510"],"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 Games","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6899999976158142,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G8715754740","display_name":null,"funder_award_id":"20200058069001","funder_id":"https://openalex.org/F4320322857","funder_display_name":"Aeronautical Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320322857","display_name":"Aeronautical Science Foundation of China","ror":"https://ror.org/02wq41p38"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2357124094","https://openalex.org/W2387399993","https://openalex.org/W2389739210","https://openalex.org/W2348924972","https://openalex.org/W2365736347","https://openalex.org/W2047454415","https://openalex.org/W2070040999","https://openalex.org/W2387293848","https://openalex.org/W2250140200","https://openalex.org/W3201942433"],"abstract_inverted_index":{"Multiagent":[0],"reinforcement":[1],"learning":[2,87],"(MARL)":[3],"has":[4],"made":[5],"remarkable":[6],"progress":[7],"in":[8,12,28,88,92],"recent":[9],"years.":[10],"However,":[11],"most":[13],"MARL":[14],"methods,":[15],"agents":[16,66],"share":[17],"a":[18,54,96],"policy":[19,72,86],"or":[20],"value":[21,132,149],"network,":[22],"which":[23,80],"is":[24,145],"easy":[25],"to":[26,41,67,108],"result":[27],"similar":[29],"behaviors":[30],"of":[31,38,49,85,139,168],"agents,":[32],"and":[33,74,99,127,143],"thus,":[34],"limits":[35],"the":[36,39,47,83,110,121,128,154,165,177],"flexibility":[37],"method":[40,64],"handle":[42],"complex":[43,89],"tasks.":[44],"To":[45],"enhance":[46],"diversity":[48],"agent":[50],"behaviors,":[51],"we":[52,94],"propose":[53],"novel":[55],"method,":[56],"making":[57],"decisions":[58,76],"from":[59,77],"different":[60,71,78],"perspectives":[61],"(MDDP).":[62],"This":[63],"enables":[65],"switch":[68],"flexibly":[69],"between":[70],"roles":[73],"make":[75],"perspectives,":[79],"can":[81],"improve":[82],"adaptability":[84],"scenarios.":[90],"Specifically,":[91],"MDDP,":[93],"design":[95],"new":[97,122],"self-attention":[98],"gated":[100],"recurrent":[101],"unit":[102],"(GRU)-based":[103],"dueling":[104],"architecture":[105],"network":[106,125,134],"(SG-DAN)":[107],"estimate":[109],"individual":[111],"<inline-formula":[112],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[113,157],"xmlns:xlink=\"http://www.w3.org/1999/xlink\"><tex-math":[114],"notation=\"LaTeX\">$Q$</tex-math></inline-formula>-values.":[115],"SG-DAN":[116],"contains":[117],"two":[118],"components:":[119],"1)":[120],"self-attention-based":[123],"role-switching":[124],"(SAR)":[126],"capable":[129],"GRU-based":[130],"state":[131,148],"estimation":[133,142],"(GSE).":[135],"SAR":[136],"takes":[137],"charge":[138],"action":[140],"advantage":[141],"GSE":[144],"responsible":[146],"for":[147],"estimation.":[150],"Experimental":[151],"results":[152],"on":[153],"challenging":[155],"<italic":[156],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">StarCraft</i>":[158],"II":[159],"micromanagement":[160],"benchmark":[161],"not":[162],"only":[163],"verify":[164],"modeling":[166],"reasonability":[167],"MDDP":[169],"but":[170],"also":[171],"demonstrate":[172],"its":[173],"performance":[174],"superiority":[175],"over":[176],"related":[178],"advanced":[179],"approaches.":[180]},"counts_by_year":[],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}