{"id":"https://openalex.org/W4410953390","doi":"https://doi.org/10.1145/3742479","title":"STPE-MARL: Spatio-Temporal Multi-Agent Population Evolution Reinforcement Learning","display_name":"STPE-MARL: Spatio-Temporal Multi-Agent Population Evolution Reinforcement Learning","publication_year":2025,"publication_date":"2025-06-02","ids":{"openalex":"https://openalex.org/W4410953390","doi":"https://doi.org/10.1145/3742479"},"language":"en","primary_location":{"id":"doi:10.1145/3742479","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3742479","pdf_url":null,"source":{"id":"https://openalex.org/S2492086750","display_name":"ACM Transactions on Intelligent Systems and Technology","issn_l":"2157-6904","issn":["2157-6904","2157-6912"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Intelligent Systems and Technology","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/A5056395476","display_name":"Kexing Peng","orcid":"https://orcid.org/0000-0002-2712-9088"},"institutions":[{"id":"https://openalex.org/I200845125","display_name":"Nanjing University of Information Science and Technology","ror":"https://ror.org/02y0rxk19","country_code":"CN","type":"education","lineage":["https://openalex.org/I200845125"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kexing Peng","raw_affiliation_strings":["School of Computer Science, Nanjing University of Information Science and Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-2712-9088","affiliations":[{"raw_affiliation_string":"School of Computer Science, Nanjing University of Information Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I200845125"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Shihao Zhu","orcid":"https://orcid.org/0009-0007-6757-1018"},"institutions":[{"id":"https://openalex.org/I200845125","display_name":"Nanjing University of Information Science and Technology","ror":"https://ror.org/02y0rxk19","country_code":"CN","type":"education","lineage":["https://openalex.org/I200845125"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shihao Zhu","raw_affiliation_strings":["School of Software, Nanjing University of Information Science and Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0007-6757-1018","affiliations":[{"raw_affiliation_string":"School of Software, Nanjing University of Information Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I200845125"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053920875","display_name":"Tinghuai Ma","orcid":"https://orcid.org/0000-0003-2320-1692"},"institutions":[{"id":"https://openalex.org/I200845125","display_name":"Nanjing University of Information Science and Technology","ror":"https://ror.org/02y0rxk19","country_code":"CN","type":"education","lineage":["https://openalex.org/I200845125"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tinghuai Ma","raw_affiliation_strings":["School of Computer Engineering, Jiangsu Ocean University, Lianyungang, China and School of Software, Nanjing University of Information Science and Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0003-2320-1692","affiliations":[{"raw_affiliation_string":"School of Computer Engineering, Jiangsu Ocean University, Lianyungang, China and School of Software, Nanjing University of Information Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I200845125"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.05183809,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"16","issue":"4","first_page":"1","last_page":"24"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9987999796867371,"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":0.9987999796867371,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9970999956130981,"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/T10100","display_name":"Metaheuristic Optimization Algorithms Research","score":0.9909999966621399,"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":0.8545459508895874},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8176286816596985},{"id":"https://openalex.org/keywords/population","display_name":"Population","score":0.5544158220291138},{"id":"https://openalex.org/keywords/marl","display_name":"Marl","score":0.5385535359382629},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5320867896080017},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3370528817176819},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.09588706493377686},{"id":"https://openalex.org/keywords/demography","display_name":"Demography","score":0.05915367603302002}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8545459508895874},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8176286816596985},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.5544158220291138},{"id":"https://openalex.org/C92927620","wikidata":"https://www.wikidata.org/wiki/Q184053","display_name":"Marl","level":3,"score":0.5385535359382629},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5320867896080017},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3370528817176819},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.09588706493377686},{"id":"https://openalex.org/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","level":1,"score":0.05915367603302002},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C109007969","wikidata":"https://www.wikidata.org/wiki/Q749565","display_name":"Structural basin","level":2,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3742479","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3742479","pdf_url":null,"source":{"id":"https://openalex.org/S2492086750","display_name":"ACM Transactions on Intelligent Systems and Technology","issn_l":"2157-6904","issn":["2157-6904","2157-6912"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Intelligent Systems and Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1042425173","display_name":null,"funder_award_id":"62372243)","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W2560674852","https://openalex.org/W2623431351","https://openalex.org/W2747329762","https://openalex.org/W2903709398","https://openalex.org/W2951278471","https://openalex.org/W2963076818","https://openalex.org/W2963762747","https://openalex.org/W2978329087","https://openalex.org/W2982316857","https://openalex.org/W2998367975","https://openalex.org/W3039459278","https://openalex.org/W3092206109","https://openalex.org/W3099303207","https://openalex.org/W3163926178","https://openalex.org/W3196792970","https://openalex.org/W4287749615","https://openalex.org/W4299802797","https://openalex.org/W4311723471","https://openalex.org/W4321650043","https://openalex.org/W4360584316","https://openalex.org/W4363675749","https://openalex.org/W4367727829","https://openalex.org/W4378501681","https://openalex.org/W4385484707","https://openalex.org/W4385566404","https://openalex.org/W4386609747","https://openalex.org/W4386929378","https://openalex.org/W4391021192","https://openalex.org/W4393335904","https://openalex.org/W4394014102","https://openalex.org/W4399772654","https://openalex.org/W4402401893","https://openalex.org/W4403331605","https://openalex.org/W4405441213","https://openalex.org/W7131266178"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W4387369504","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"Achieving":[0],"joint":[1],"goals":[2],"efficiently":[3],"in":[4,32,116,122,129,154,158],"complex":[5,118],"real-world":[6],"tasks":[7,121],"demands":[8],"effective":[9],"collaboration":[10],"among":[11],"multiple":[12],"agents.":[13],"Multi-Agent":[14],"Reinforcement":[15],"Learning":[16],"(MARL)":[17],"faces":[18],"two":[19,117],"interrelated":[20],"challenges:":[21],"limited":[22],"exploration":[23,63,155],"leads":[24],"to":[25,77,100],"early":[26],"convergence":[27,143],"on":[28],"suboptimal":[29],"behaviors,":[30],"which":[31],"turn":[33],"exacerbates":[34],"non-stationarity":[35],"under":[36],"partial":[37,79],"observability.":[38],"To":[39],"address":[40],"these":[41],"issues,":[42],"we":[43],"propose":[44],"a":[45],"novel":[46],"framework,":[47],"Spatio-Temporal":[48],"Multi-agent":[49],"Population":[50],"Evolution":[51],"(STPE-MARL).":[52],"By":[53],"integrating":[54],"Evolutionary":[55],"Algorithms":[56],"(EAs)":[57],"with":[58],"MARL,":[59],"our":[60],"method":[61],"enhances":[62],"diversity":[64],"and":[65,95,105,125,144,156],"facilitates":[66],"global":[67],"policy":[68,142],"optimization.":[69],"We":[70,113],"further":[71],"incorporate":[72],"Graph":[73,93,96],"Neural":[74],"Networks":[75],"(GNNs)":[76],"mitigate":[78],"observability":[80],"by":[81],"encoding":[82],"permutation":[83],"symmetry":[84],"through":[85,109],"graph-based":[86],"message":[87],"passing.":[88],"Two":[89],"GNN-based":[90],"training":[91],"modes,":[92],"Relation":[94],"Decomposition,":[97],"are":[98],"introduced":[99],"extend":[101],"agents\u2019":[102],"receptive":[103],"fields":[104],"capture":[106],"spatio-temporal":[107],"dependencies":[108],"time-series":[110],"trajectory":[111],"sampling.":[112],"evaluate":[114],"STPE-MARL":[115,139],"environments:":[119],"micromanagement":[120],"StarCraft":[123],"II":[124],"large-scale":[126],"traffic":[127],"simulations":[128],"SUMO":[130],"(Simulation":[131],"of":[132,152],"Urban":[133],"MObility).":[134],"Experimental":[135],"results":[136],"demonstrate":[137],"that":[138],"significantly":[140],"improves":[141],"outperforms":[145],"baseline":[146],"methods,":[147],"highlighting":[148],"the":[149],"complementary":[150],"roles":[151],"EAs":[153],"GNNs":[157],"addressing":[159],"observation":[160],"limitations.":[161]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}