{"id":"https://openalex.org/W4386323678","doi":"https://doi.org/10.1109/jcc59055.2023.00007","title":"Bi-level Multi-Agent Actor-Critic Methods with ransformers","display_name":"Bi-level Multi-Agent Actor-Critic Methods with ransformers","publication_year":2023,"publication_date":"2023-07-01","ids":{"openalex":"https://openalex.org/W4386323678","doi":"https://doi.org/10.1109/jcc59055.2023.00007"},"language":"en","primary_location":{"id":"doi:10.1109/jcc59055.2023.00007","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jcc59055.2023.00007","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Joint Cloud Computing (JCC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5061252955","display_name":"Tianjiao Wan","orcid":"https://orcid.org/0000-0002-2423-4982"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianjiao Wan","raw_affiliation_strings":["National University of Defense Technology,Changsha,China","National University of Defense Technology, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025503287","display_name":"Haibo Mi","orcid":"https://orcid.org/0000-0003-3615-5912"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haibo Mi","raw_affiliation_strings":["National University of Defense Technology,Wuhan,China","National University of Defense Technology, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,Wuhan,China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"National University of Defense Technology, Wuhan, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016262505","display_name":"Zijian Gao","orcid":"https://orcid.org/0000-0001-5151-3381"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zijian Gao","raw_affiliation_strings":["National University of Defense Technology,Changsha,China","National University of Defense Technology, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073132517","display_name":"Yuanzhao Zhai","orcid":"https://orcid.org/0000-0003-1385-0074"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanzhao Zhai","raw_affiliation_strings":["National University of Defense Technology,Changsha,China","National University of Defense Technology, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088885490","display_name":"Bo Ding","orcid":"https://orcid.org/0000-0002-1236-8318"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Ding","raw_affiliation_strings":["National University of Defense Technology,Changsha,China","National University of Defense Technology, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039795290","display_name":"Dawei Feng","orcid":"https://orcid.org/0000-0002-7587-8905"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dawei Feng","raw_affiliation_strings":["National University of Defense Technology,Changsha,China","National University of Defense Technology, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"9","last_page":"16"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991000294685364,"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":0.9991000294685364,"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.97079998254776,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11195","display_name":"Simulation Techniques and Applications","score":0.9621999859809875,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6874738931655884},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.41763049364089966},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.27607429027557373}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6874738931655884},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.41763049364089966},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27607429027557373}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/jcc59055.2023.00007","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jcc59055.2023.00007","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Joint Cloud Computing (JCC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.5299999713897705,"display_name":"Reduced inequalities"},{"id":"https://metadata.un.org/sdg/16","score":0.41999998688697815,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W1191599655","https://openalex.org/W2098877483","https://openalex.org/W2166533447","https://openalex.org/W2292533394","https://openalex.org/W2602275733","https://openalex.org/W2617547828","https://openalex.org/W2626637010","https://openalex.org/W2736601468","https://openalex.org/W2740377041","https://openalex.org/W2747213132","https://openalex.org/W2894976951","https://openalex.org/W2973229164","https://openalex.org/W3029584598","https://openalex.org/W3046288222","https://openalex.org/W3123636359","https://openalex.org/W3163926178","https://openalex.org/W3176265013","https://openalex.org/W4286748781","https://openalex.org/W4287757834","https://openalex.org/W4288594419","https://openalex.org/W4297098279","https://openalex.org/W4297098301","https://openalex.org/W4299802797","https://openalex.org/W4300830895","https://openalex.org/W4301311528","https://openalex.org/W4385245566","https://openalex.org/W6627932998","https://openalex.org/W6674657456","https://openalex.org/W6684205842","https://openalex.org/W6685388067","https://openalex.org/W6685444567","https://openalex.org/W6734678876","https://openalex.org/W6738796088","https://openalex.org/W6739516088","https://openalex.org/W6740217080","https://openalex.org/W6741002519","https://openalex.org/W6742529797","https://openalex.org/W6749304979","https://openalex.org/W6755069753","https://openalex.org/W6758846586","https://openalex.org/W6762491519","https://openalex.org/W6777981532","https://openalex.org/W6781750019","https://openalex.org/W6787618087","https://openalex.org/W6789172296","https://openalex.org/W6795908048","https://openalex.org/W6796436736","https://openalex.org/W6840380725","https://openalex.org/W6864424756"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Recently,":[0],"deep":[1],"multi-agent":[2,11,24,58,121,138,156],"reinforcement":[3,60,122,157],"learning":[4,61,123,158],"methods":[5,26,159],"have":[6],"witnessed":[7],"great":[8],"progress,":[9],"including":[10,137],"actor-critic":[12,25,120,166],"methods.":[13,30],"However,":[14],"it\u2019s":[15],"worth":[16],"noticing":[17],"there":[18],"is":[19,111],"a":[20,55,70,142],"performance":[21,41,162],"gap":[22],"between":[23],"and":[27,38,46,82,106,128,141,167],"state-of-the-art":[28,165],"value-based":[29,168],"In":[31,91],"this":[32],"paper,":[33],"we":[34,53,68,93],"investigate":[35],"the":[36,88,95,99],"causes":[37],"attribute":[39],"inferior":[40],"to":[42,77,102,115],"issues":[43],"of":[44,145],"contribution-mismatch":[45],"indiscriminate":[47],"guidance.":[48],"To":[49],"overcome":[50],"these":[51],"problems,":[52],"introduce":[54],"novel":[56],"bi-level":[57,74],"actorcritic":[59],"approach":[62],"with":[63,131],"transformers,":[64],"called":[65],"BMT.":[66],"Specifically,":[67],"propose":[69],"simple":[71],"but":[72],"efficient":[73],"optimization":[75],"mechanism":[76],"learn":[78],"both":[79,164],"global":[80],"critic":[81],"agentspecific":[83],"critic,":[84],"thus":[85],"jointly":[86],"guiding":[87],"policy":[89,100],"update.":[90],"addition,":[92],"adopt":[94],"transformer-based":[96],"model":[97],"as":[98,126],"network":[101],"decouple":[103],"complicated":[104],"relationships":[105],"generate":[107],"flexible":[108],"policy.":[109],"BMT":[110],"also":[112],"general":[113],"enough":[114],"be":[116],"plugged":[117],"into":[118],"any":[119],"approach,":[124],"such":[125],"MAPPO,":[127],"equips":[129],"it":[130],"strong":[132],"expression.":[133],"On":[134],"multiple":[135],"benchmarks":[136],"particle":[139],"environments":[140],"challenging":[143],"set":[144],"StarCraft":[146],"II":[147],"micromanagement":[148],"tasks,":[149],"large-scale":[150],"empirical":[151],"experiments":[152],"demonstrate":[153],"that":[154],"BMT-based":[155],"achieve":[160],"superior":[161],"over":[163],"approaches.":[169]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
