{"id":"https://openalex.org/W4414930153","doi":"https://doi.org/10.1109/icmla66185.2025.00157","title":"Enhancing Multi-Agent Collaboration with Attention-Based Actor-Critic Policies","display_name":"Enhancing Multi-Agent Collaboration with Attention-Based Actor-Critic Policies","publication_year":2025,"publication_date":"2025-12-03","ids":{"openalex":"https://openalex.org/W4414930153","doi":"https://doi.org/10.1109/icmla66185.2025.00157"},"language":"en","primary_location":{"id":"doi:10.1109/icmla66185.2025.00157","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmla66185.2025.00157","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Machine Learning and Applications (ICMLA)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2507.22782","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Hugo Garrido-Lestache Belinchon","orcid":null},"institutions":[{"id":"https://openalex.org/I50702494","display_name":"Milwaukee School of Engineering","ror":"https://ror.org/04h7cfr36","country_code":"US","type":"education","lineage":["https://openalex.org/I50702494"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hugo Garrido-Lestache Belinchon","raw_affiliation_strings":["Milwaukee School of Engineering,Diercks School of Advanced Computing,Milwaukee,WI,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Milwaukee School of Engineering,Diercks School of Advanced Computing,Milwaukee,WI,USA","institution_ids":["https://openalex.org/I50702494"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5119891858","display_name":"Jeremy Kedziora","orcid":null},"institutions":[{"id":"https://openalex.org/I50702494","display_name":"Milwaukee School of Engineering","ror":"https://ror.org/04h7cfr36","country_code":"US","type":"education","lineage":["https://openalex.org/I50702494"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jeremy Kedziora","raw_affiliation_strings":["Milwaukee School of Engineering,Diercks School of Advanced Computing,Milwaukee,WI,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Milwaukee School of Engineering,Diercks School of Advanced Computing,Milwaukee,WI,USA","institution_ids":["https://openalex.org/I50702494"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I50702494"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.30233185,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1034","last_page":"1039"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11810","display_name":"Complex Systems and Decision Making","score":0.7251999974250793,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11810","display_name":"Complex Systems and Decision Making","score":0.7251999974250793,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10970","display_name":"Team Dynamics and Performance","score":0.690500020980835,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10703","display_name":"Business Process Modeling and Analysis","score":0.6895999908447266,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7523999810218811},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.6880999803543091},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5938000082969666},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.5662999749183655},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.44130000472068787},{"id":"https://openalex.org/keywords/possession","display_name":"Possession (linguistics)","score":0.3628000020980835},{"id":"https://openalex.org/keywords/exponential-growth","display_name":"Exponential growth","score":0.32749998569488525}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7523999810218811},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6959999799728394},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.6880999803543091},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5938000082969666},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.5662999749183655},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.44130000472068787},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.39570000767707825},{"id":"https://openalex.org/C2780193096","wikidata":"https://www.wikidata.org/wiki/Q3543662","display_name":"Possession (linguistics)","level":2,"score":0.3628000020980835},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34049999713897705},{"id":"https://openalex.org/C75235859","wikidata":"https://www.wikidata.org/wiki/Q582659","display_name":"Exponential growth","level":2,"score":0.32749998569488525},{"id":"https://openalex.org/C138020889","wikidata":"https://www.wikidata.org/wiki/Q2349659","display_name":"Collaborative learning","level":2,"score":0.32199999690055847},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2833999991416931},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.27709999680519104},{"id":"https://openalex.org/C122041747","wikidata":"https://www.wikidata.org/wiki/Q838611","display_name":"Ball (mathematics)","level":2,"score":0.271699994802475},{"id":"https://openalex.org/C3018790387","wikidata":"https://www.wikidata.org/wiki/Q869010","display_name":"Hybrid learning","level":2,"score":0.26829999685287476},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.26440000534057617},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.2614000141620636},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.257999986410141}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icmla66185.2025.00157","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmla66185.2025.00157","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Machine Learning and Applications (ICMLA)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2507.22782","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.22782","pdf_url":"https://arxiv.org/pdf/2507.22782","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":"doi:10.48550/arxiv.2507.22782","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.22782","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2507.22782","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.22782","pdf_url":"https://arxiv.org/pdf/2507.22782","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":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"This":[0,34],"paper":[1],"introduces":[2],"Team-Attention-Actor-Critic":[3],"(TAAC),":[4],"a":[5,19,57,65,81,111],"reinforcement":[6],"learning":[7],"algorithm":[8],"designed":[9],"to":[10,42],"enhance":[11],"multi-agent":[12,90],"collaboration":[13],"in":[14,28,80],"cooperative":[15],"environments.":[16],"TAAC":[17,79,102],"employs":[18],"Centralized":[20],"Training/Centralized":[21],"Execution":[22],"scheme":[23],"incorporating":[24],"multi-headed":[25],"attention":[26],"mechanisms":[27],"both":[29],"the":[30,49],"actor":[31],"and":[32,96,106,126],"critic.":[33],"design":[35],"facilitates":[36],"dynamic,":[37],"inter-agent":[38,121],"communication,":[39],"allowing":[40],"agents":[41],"explicitly":[43],"query":[44],"teammates,":[45],"thereby":[46],"efficiently":[47],"managing":[48],"exponential":[50],"growth":[51],"of":[52,60,113],"joint-action":[53],"spaces":[54],"while":[55],"ensuring":[56],"high":[58],"degree":[59],"collaboration.":[61],"We":[62,77,99],"further":[63],"introduce":[64],"penalized":[66],"loss":[67],"function":[68],"which":[69],"promotes":[70],"diverse":[71],"yet":[72],"complementary":[73],"roles":[74],"among":[75],"agents.":[76],"evaluate":[78],"simulated":[82],"soccer":[83],"environment":[84],"against":[85],"benchmark":[86],"algorithms":[87],"representing":[88],"other":[89],"paradigms,":[91],"including":[92],"Proximal":[93],"Policy":[94],"Optimization":[95],"Multi-Agent":[97],"Actor-Attention-Critic.":[98],"find":[100],"that":[101],"exhibits":[103],"superior":[104],"performance":[105],"enhanced":[107],"collaborative":[108],"behaviors":[109],"across":[110],"variety":[112],"metrics":[114],"(win":[115],"rates,":[116],"goal":[117],"differentials,":[118],"Elo":[119],"ratings,":[120],"connectivity,":[122],"balanced":[123],"spatial":[124],"distributions,":[125],"frequent":[127],"tactical":[128],"interactions":[129],"such":[130],"as":[131],"ball":[132],"possession":[133],"swaps).":[134]},"counts_by_year":[],"updated_date":"2026-05-20T08:49:12.498775","created_date":"2025-10-10T00:00:00"}