{"id":"https://openalex.org/W4407205740","doi":"https://doi.org/10.1177/02783649241306124","title":"Asynchronous multi-agent deep reinforcement learning under partial observability","display_name":"Asynchronous multi-agent deep reinforcement learning under partial observability","publication_year":2025,"publication_date":"2025-02-06","ids":{"openalex":"https://openalex.org/W4407205740","doi":"https://doi.org/10.1177/02783649241306124"},"language":"en","primary_location":{"id":"doi:10.1177/02783649241306124","is_oa":true,"landing_page_url":"https://doi.org/10.1177/02783649241306124","pdf_url":null,"source":{"id":"https://openalex.org/S73484101","display_name":"The International Journal of Robotics Research","issn_l":"0278-3649","issn":["0278-3649","1741-3176"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of Robotics Research","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1177/02783649241306124","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102946527","display_name":"Yuchen Xiao","orcid":"https://orcid.org/0000-0003-1038-1882"},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]},{"id":"https://openalex.org/I87182695","display_name":"Universidad del Noreste","ror":"https://ror.org/02ahky613","country_code":"MX","type":"education","lineage":["https://openalex.org/I87182695"]}],"countries":["MX","US"],"is_corresponding":true,"raw_author_name":"Yuchen Xiao","raw_affiliation_strings":["Northeastern University","Khoury College of Computer Science, Northeastern University, Boston, MA, USA"],"affiliations":[{"raw_affiliation_string":"Northeastern University","institution_ids":["https://openalex.org/I87182695"]},{"raw_affiliation_string":"Khoury College of Computer Science, Northeastern University, Boston, MA, USA","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024313207","display_name":"Weihao Tan","orcid":"https://orcid.org/0000-0002-5888-6081"},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]},{"id":"https://openalex.org/I87182695","display_name":"Universidad del Noreste","ror":"https://ror.org/02ahky613","country_code":"MX","type":"education","lineage":["https://openalex.org/I87182695"]}],"countries":["MX","US"],"is_corresponding":false,"raw_author_name":"Weihao Tan","raw_affiliation_strings":["Northeastern University","Khoury College of Computer Science, Northeastern University, Boston, MA, USA"],"affiliations":[{"raw_affiliation_string":"Northeastern University","institution_ids":["https://openalex.org/I87182695"]},{"raw_affiliation_string":"Khoury College of Computer Science, Northeastern University, Boston, MA, USA","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059983157","display_name":"Joshua Hoffman","orcid":"https://orcid.org/0000-0003-2823-1866"},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]},{"id":"https://openalex.org/I87182695","display_name":"Universidad del Noreste","ror":"https://ror.org/02ahky613","country_code":"MX","type":"education","lineage":["https://openalex.org/I87182695"]}],"countries":["MX","US"],"is_corresponding":false,"raw_author_name":"Joshua Hoffman","raw_affiliation_strings":["Northeastern University","Khoury College of Computer Science, Northeastern University, Boston, MA, USA"],"affiliations":[{"raw_affiliation_string":"Northeastern University","institution_ids":["https://openalex.org/I87182695"]},{"raw_affiliation_string":"Khoury College of Computer Science, Northeastern University, Boston, MA, USA","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101603610","display_name":"Tian Xia","orcid":"https://orcid.org/0009-0001-2527-4257"},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]},{"id":"https://openalex.org/I87182695","display_name":"Universidad del Noreste","ror":"https://ror.org/02ahky613","country_code":"MX","type":"education","lineage":["https://openalex.org/I87182695"]}],"countries":["MX","US"],"is_corresponding":false,"raw_author_name":"Tian Xia","raw_affiliation_strings":["Northeastern University","Khoury College of Computer Science, Northeastern University, Boston, MA, USA"],"affiliations":[{"raw_affiliation_string":"Northeastern University","institution_ids":["https://openalex.org/I87182695"]},{"raw_affiliation_string":"Khoury College of Computer Science, Northeastern University, Boston, MA, USA","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033129735","display_name":"Christopher Amato","orcid":"https://orcid.org/0000-0002-6786-7384"},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]},{"id":"https://openalex.org/I87182695","display_name":"Universidad del Noreste","ror":"https://ror.org/02ahky613","country_code":"MX","type":"education","lineage":["https://openalex.org/I87182695"]}],"countries":["MX","US"],"is_corresponding":false,"raw_author_name":"Christopher Amato","raw_affiliation_strings":["Northeastern University","Khoury College of Computer Science, Northeastern University, Boston, MA, USA"],"affiliations":[{"raw_affiliation_string":"Northeastern University","institution_ids":["https://openalex.org/I87182695"]},{"raw_affiliation_string":"Khoury College of Computer Science, Northeastern University, Boston, MA, USA","institution_ids":["https://openalex.org/I12912129"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5102946527"],"corresponding_institution_ids":["https://openalex.org/I12912129","https://openalex.org/I87182695"],"apc_list":null,"apc_paid":null,"fwci":9.8466,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.97340369,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":"44","issue":"8","first_page":"1257","last_page":"1286"},"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/T14011","display_name":"Elevator Systems and Control","score":0.9927999973297119,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9911999702453613,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/observability","display_name":"Observability","score":0.9051580429077148},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8181601762771606},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.6546030640602112},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5951458215713501},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5903103947639465},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4417414367198944},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.24497440457344055},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21307820081710815},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.08548712730407715}],"concepts":[{"id":"https://openalex.org/C36299963","wikidata":"https://www.wikidata.org/wiki/Q1369844","display_name":"Observability","level":2,"score":0.9051580429077148},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8181601762771606},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.6546030640602112},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5951458215713501},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5903103947639465},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4417414367198944},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.24497440457344055},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21307820081710815},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.08548712730407715},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1177/02783649241306124","is_oa":true,"landing_page_url":"https://doi.org/10.1177/02783649241306124","pdf_url":null,"source":{"id":"https://openalex.org/S73484101","display_name":"The International Journal of Robotics Research","issn_l":"0278-3649","issn":["0278-3649","1741-3176"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of Robotics Research","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1177/02783649241306124","is_oa":true,"landing_page_url":"https://doi.org/10.1177/02783649241306124","pdf_url":null,"source":{"id":"https://openalex.org/S73484101","display_name":"The International Journal of Robotics Research","issn_l":"0278-3649","issn":["0278-3649","1741-3176"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of Robotics Research","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G246041870","display_name":null,"funder_award_id":"W911NF20-1-0265","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"},{"id":"https://openalex.org/G4476123902","display_name":null,"funder_award_id":"N00014-19-1-2131","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"}],"funders":[{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"},{"id":"https://openalex.org/F4320338281","display_name":"Army Research Office","ror":"https://ror.org/05epdh915"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W59183349","https://openalex.org/W1641379095","https://openalex.org/W1670739992","https://openalex.org/W1981276685","https://openalex.org/W2064675550","https://openalex.org/W2071444114","https://openalex.org/W2091482777","https://openalex.org/W2108892923","https://openalex.org/W2109910161","https://openalex.org/W2141559645","https://openalex.org/W2145339207","https://openalex.org/W2157331557","https://openalex.org/W2166533447","https://openalex.org/W2290743114","https://openalex.org/W2292533394","https://openalex.org/W2296434941","https://openalex.org/W2408811396","https://openalex.org/W2492794003","https://openalex.org/W2567614470","https://openalex.org/W2597337536","https://openalex.org/W2602753196","https://openalex.org/W2606126444","https://openalex.org/W2612972698","https://openalex.org/W2617547828","https://openalex.org/W2743150096","https://openalex.org/W2743858345","https://openalex.org/W2746553466","https://openalex.org/W2747213132","https://openalex.org/W2757564505","https://openalex.org/W2787066086","https://openalex.org/W2894976951","https://openalex.org/W2915338839","https://openalex.org/W2924816077","https://openalex.org/W2944827102","https://openalex.org/W2962930314","https://openalex.org/W2963041255","https://openalex.org/W2963353662","https://openalex.org/W2964227312","https://openalex.org/W2967349569","https://openalex.org/W2972122474","https://openalex.org/W3005850366","https://openalex.org/W3016361525","https://openalex.org/W3041202696","https://openalex.org/W3096656822","https://openalex.org/W3099587965","https://openalex.org/W3099815795","https://openalex.org/W3102824929","https://openalex.org/W3148143011","https://openalex.org/W3176265013","https://openalex.org/W3177023080","https://openalex.org/W3206518075"],"related_works":["https://openalex.org/W2046459260","https://openalex.org/W2967463586","https://openalex.org/W2074679142","https://openalex.org/W2765830098","https://openalex.org/W1971989957","https://openalex.org/W2517338020","https://openalex.org/W3157641275","https://openalex.org/W4312300846","https://openalex.org/W2104042711","https://openalex.org/W4206221578"],"abstract_inverted_index":{"The":[0,176],"state-of-the-art":[1],"multi-agent":[2,167],"reinforcement":[3],"learning":[4,78,88,92,158],"(MARL)":[5],"methods":[6,18,135,184,196],"provide":[7],"promising":[8],"solutions":[9,162],"to":[10,42],"a":[11,27,59,109,144],"variety":[12,145],"of":[13,61,111,146,154],"complex":[14],"problems.":[15],"Yet,":[16],"these":[17],"all":[19],"assume":[20],"that":[21,38,169],"agents":[22,75,122],"perform":[23,76],"primitive":[24],"actions":[25,188],"in":[26,84,128,137,165,197],"synchronized":[28],"manner,":[29],"making":[30],"them":[31],"impractical":[32],"for":[33,66,98,157,185,194],"long-horizon":[34],"real-world":[35],"multi-robot":[36],"tasks":[37],"inherently":[39],"require":[40],"robots":[41,142],"asynchronously":[43],"reason":[44],"about":[45],"action":[46],"selection":[47],"at":[48],"varying":[49],"time":[50],"durations.":[51],"To":[52],"solve":[53],"this":[54],"problem,":[55],"we":[56,107],"first":[57,181],"propose":[58],"group":[60],"value-based":[62],"cooperative":[63],"MARL":[64,183],"approaches":[65,178],"asynchronous":[67,77,130,161],"execution":[68,100],"using":[69],"temporally":[70,186],"extended":[71,187],"macro-actions":[72,164],".":[73],"Here,":[74],"and":[79,89,93,95,139,160,189],"decision-making":[80],"with":[81,163],"macro-action-value":[82],"functions":[83],"three":[85,118],"paradigms:":[86],"decentralized":[87,99],"control,":[90,94],"centralized":[91,96],"training":[97,119],"(CTDE).":[101],"Building":[102],"on":[103,140],"the":[104,117,152,180,192,198],"above":[105],"work,":[106],"formulate":[108],"set":[110],"macro-action-based":[112],"policy":[113],"gradient":[114],"algorithms":[115,156],"under":[116],"paradigms,":[120],"where":[121],"directly":[123],"optimize":[124],"their":[125],"parameterized":[126],"policies":[127],"an":[129],"manner.":[131],"We":[132],"evaluate":[133],"our":[134,155],"both":[136],"simulation":[138],"real":[141],"over":[143],"realistic":[147],"domains.":[148],"Empirical":[149],"results":[150],"demonstrate":[151],"effectiveness":[153],"high-quality":[159],"large":[166],"problems":[168],"were":[170],"previously":[171],"unsolvable":[172],"via":[173],"primitive-action-based":[174],"approaches.":[175],"proposed":[177],"represent":[179],"general":[182],"serve":[190],"as":[191],"foundation":[193],"future":[195],"area.":[199]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2}],"updated_date":"2026-04-01T17:29:45.350535","created_date":"2025-10-10T00:00:00"}