{"id":"https://openalex.org/W4415428019","doi":"https://doi.org/10.3233/faia251261","title":"ToMacVF: Temporal Macro-Action Value Factorization for Asynchronous Multi-Agent Reinforcement Learning","display_name":"ToMacVF: Temporal Macro-Action Value Factorization for Asynchronous Multi-Agent Reinforcement Learning","publication_year":2025,"publication_date":"2025-10-21","ids":{"openalex":"https://openalex.org/W4415428019","doi":"https://doi.org/10.3233/faia251261"},"language":null,"primary_location":{"id":"doi:10.3233/faia251261","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia251261","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"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":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.3233/faia251261","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100407200","display_name":"Wenjing Zhang","orcid":"https://orcid.org/0009-0009-8472-5220"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wenjing Zhang","raw_affiliation_strings":["Harbin Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100614543","display_name":"Wei Zhang","orcid":"https://orcid.org/0000-0002-0598-4606"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Zhang","raw_affiliation_strings":["Harbin Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100407200"],"corresponding_institution_ids":["https://openalex.org/I204983213"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.49569344,"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":0.9233999848365784,"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":0.9233999848365784,"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/asynchronous-communication","display_name":"Asynchronous communication","score":0.7864999771118164},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6424999833106995},{"id":"https://openalex.org/keywords/factorization","display_name":"Factorization","score":0.6378999948501587},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4489000141620636},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.39570000767707825},{"id":"https://openalex.org/keywords/adaptability","display_name":"Adaptability","score":0.3671000003814697},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.362199991941452}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7886999845504761},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.7864999771118164},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6424999833106995},{"id":"https://openalex.org/C187834632","wikidata":"https://www.wikidata.org/wiki/Q188804","display_name":"Factorization","level":2,"score":0.6378999948501587},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4489000141620636},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.39570000767707825},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.38749998807907104},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.3671000003814697},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3652999997138977},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.362199991941452},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.35350000858306885},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.3239000141620636},{"id":"https://openalex.org/C116409475","wikidata":"https://www.wikidata.org/wiki/Q1385056","display_name":"External Data Representation","level":2,"score":0.3174000084400177},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3052000105381012},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.30239999294281006},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.27709999680519104},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.2759000062942505},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.2703999876976013},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.25440001487731934}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/faia251261","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia251261","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"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":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.3233/faia251261","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia251261","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"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":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"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":{"Existing":[0],"asynchronous":[1,118,184,203],"MARL":[2,28],"methods":[3,29,37],"based":[4,133],"on":[5,30,146],"MacDec-POMDP":[6],"typically":[7],"construct":[8],"training":[9,78],"trajectory":[10],"buffers":[11],"by":[12],"simply":[13],"sampling":[14],"limited":[15],"and":[16,24,42,97,106,116,126,199],"biased":[17],"data":[18],"at":[19],"the":[20,31,46,59,110,121,142,166,175],"endpoints":[21],"of":[22,45,109,174],"macro-actions,":[23],"directly":[25],"apply":[26],"conventional":[27],"buffers.":[32],"As":[33],"a":[34,103,148],"result,":[35],"these":[36,57],"lead":[38],"to":[39,67,90,94,158,183],"an":[40,172],"incomplete":[41],"inaccurate":[43],"representation":[44,108],"macro-action":[47,74,99,111,128],"execution":[48,100],"process,":[49],"along":[50],"with":[51,92],"unsuitable":[52],"credit":[53,71],"assignments.":[54],"To":[55,113],"solve":[56],"problems,":[58],"Temporal":[60,131],"Macro-action":[61,81,132],"Value":[62],"Factorization":[63],"(ToMacVF)":[64],"is":[65,88,136,156,169],"proposed":[66],"achieve":[68],"fine-grained":[69,117],"temporal":[70],"assignment":[72],"for":[73],"contributions.":[75],"A":[76],"centralized":[77],"buffer,":[79],"called":[80,130],"Segmented":[82],"Joint":[83],"Experience":[84],"Replay":[85],"Trajectory":[86],"(Mac-SJERT),":[87],"designed":[89,157],"incorporate":[91],"ToMacVF":[93,150,167,176,187],"collect":[95],"accurate":[96],"complete":[98],"information,":[101],"supporting":[102],"more":[104],"comprehensive":[105],"precise":[107],"process.":[112],"ensure":[114],"principled":[115],"value":[119,162],"factorization,":[120],"consistency":[122],"requirement":[123],"between":[124],"joint":[125],"individual":[127],"selection":[129],"IGM":[134],"(To-Mac-IGM)":[135],"formalized,":[137],"proving":[138],"that":[139],"it":[140],"generalizes":[141],"synchronous":[143],"cases.":[144],"Based":[145],"To-Mac-IGM,":[147],"modularized":[149],"architecture,":[151],"which":[152],"satisfies":[153],"CTDE":[154],"principle,":[155],"conveniently":[159],"integrate":[160],"previous":[161],"factorization":[163],"methods.":[164],"Next,":[165],"algorithm":[168,188],"devised":[170],"as":[171],"implementation":[173],"architecture.":[177],"Experimental":[178],"results":[179],"demonstrate":[180],"that,":[181],"compared":[182],"baselines,":[185],"our":[186],"not":[189],"only":[190],"achieves":[191],"optimal":[192],"performance":[193],"but":[194],"also":[195],"exhibits":[196],"strong":[197],"adaptability":[198],"robustness":[200],"across":[201],"various":[202],"multi-agent":[204],"experimental":[205],"scenarios.":[206]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-24T00:00:00"}