{"id":"https://openalex.org/W4408345777","doi":"https://doi.org/10.1109/icassp49660.2025.10889127","title":"A Ranking Scheme for Trust Region Multi-agent Reinforcement Learning","display_name":"A Ranking Scheme for Trust Region Multi-agent Reinforcement Learning","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408345777","doi":"https://doi.org/10.1109/icassp49660.2025.10889127"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889127","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889127","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5080946698","display_name":"Ruichen Gao","orcid":null},"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":"Ruichen Gao","raw_affiliation_strings":["Harbin Institute of Technology,Harbin,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Harbin,China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042174429","display_name":"Yi Hu","orcid":"https://orcid.org/0000-0001-9319-5692"},"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":"Yi Hu","raw_affiliation_strings":["Harbin Institute of Technology,Harbin,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Harbin,China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Deqin Zheng","orcid":null},"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":"Deqin Zheng","raw_affiliation_strings":["Harbin Institute of Technology,Harbin,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Harbin,China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088246826","display_name":"Mengxuan Shao","orcid":null},"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":"Mengxuan Shao","raw_affiliation_strings":["Harbin Institute of Technology,Harbin,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Harbin,China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001634212","display_name":"Haiqi Zhu","orcid":"https://orcid.org/0000-0002-5076-2412"},"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":"Haiqi Zhu","raw_affiliation_strings":["Harbin Institute of Technology,Harbin,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Harbin,China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111363034","display_name":"Chenyue Song","orcid":null},"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":"Chenyue Song","raw_affiliation_strings":["Harbin Institute of Technology,Harbin,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Harbin,China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100740183","display_name":"Wei Zhang","orcid":"https://orcid.org/0000-0001-6427-3946"},"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,Harbin,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Harbin,China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054864573","display_name":"Feng Jiang","orcid":"https://orcid.org/0000-0001-8342-1211"},"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":"Feng Jiang","raw_affiliation_strings":["Harbin Institute of Technology,Harbin,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Harbin,China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"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":0.02456819,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.5404000282287598,"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":0.5404000282287598,"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":0.8638222813606262},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7202528119087219},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.7077741026878357},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.7069277763366699},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5057075023651123},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4346136152744293},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11091020703315735},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.10174810886383057},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.08656740188598633}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8638222813606262},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7202528119087219},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.7077741026878357},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.7069277763366699},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5057075023651123},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4346136152744293},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11091020703315735},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.10174810886383057},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.08656740188598633},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889127","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889127","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W2145339207","https://openalex.org/W2617547828","https://openalex.org/W2951360122","https://openalex.org/W2997072274","https://openalex.org/W3011672202","https://openalex.org/W3167206788","https://openalex.org/W3204192621","https://openalex.org/W4220744054","https://openalex.org/W4293518946","https://openalex.org/W4293519295","https://openalex.org/W4352993948","https://openalex.org/W4385486275","https://openalex.org/W4385644834","https://openalex.org/W4390814006","https://openalex.org/W4395049132","https://openalex.org/W4402402057","https://openalex.org/W6627932998","https://openalex.org/W6638018090","https://openalex.org/W6675811377","https://openalex.org/W6683204974","https://openalex.org/W6684205842","https://openalex.org/W6738796088","https://openalex.org/W6739516088","https://openalex.org/W6744537943","https://openalex.org/W6747473740","https://openalex.org/W6747941106","https://openalex.org/W6758507868","https://openalex.org/W6758846586","https://openalex.org/W6762491519","https://openalex.org/W6766805167","https://openalex.org/W6773620346","https://openalex.org/W6786364697","https://openalex.org/W6791976426","https://openalex.org/W6800877681","https://openalex.org/W6802002411","https://openalex.org/W6802325372","https://openalex.org/W6838682728","https://openalex.org/W6840380725","https://openalex.org/W6844628001","https://openalex.org/W6851389620","https://openalex.org/W6858809654","https://openalex.org/W6866157721","https://openalex.org/W7064929991"],"related_works":["https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588","https://openalex.org/W2086122291","https://openalex.org/W1987513656"],"abstract_inverted_index":{"In":[0],"multi-agent":[1,19,31],"reinforcement":[2],"learning":[3],"(MARL),":[4],"trust":[5],"region":[6],"(TR)":[7],"methods":[8,36,55,136,161],"are":[9,46],"widely":[10],"used":[11],"because":[12],"they":[13],"effectively":[14],"mitigate":[15],"the":[16,30,62,121],"nonstationarity":[17],"of":[18,86,143],"systems":[20],"and":[21,60,73,95,116,137,147,178],"facilitate":[22],"collaboration":[23],"among":[24],"diverse":[25],"agent":[26,180],"types.":[27],"Based":[28],"on":[29,81,140,175],"advantage":[32],"decomposition":[33],"lemma,":[34],"TR":[35,54,135,160],"adopt":[37],"a":[38,49,57,65,141],"sequential":[39],"update":[40],"scheme":[41,59],"(i.e.,":[42],"agents\u2019":[43,82,87],"policy":[44,88],"networks":[45],"trained":[47],"with":[48,105,123],"certain":[50],"order).":[51],"However,":[52],"current":[53,159],"lack":[56],"ranking":[58,93,99,155],"train":[61],"agents":[63,104,122],"in":[64,70,126,162,166],"random":[66],"order,":[67],"this":[68,78],"results":[69,151],"suboptimal":[71],"performance":[72],"large":[74],"variances.":[75],"To":[76],"solve":[77],"issue,":[79],"based":[80],"observations":[83,107],"(the":[84],"input":[85],"networks),":[89],"we":[90,102],"formulate":[91],"our":[92,98,131,154],"criteria":[94],"furthermore":[96],"propose":[97],"schemes.":[100],"Specifically,":[101],"avoid":[103],"similar":[106],"being":[108],"ranked":[109],"adjacent":[110],"to":[111,120,133],"each":[112],"other":[113],"for":[114],"training":[115],"give":[117],"higher":[118],"priority":[119],"more":[124],"information":[125],"their":[127],"observations.":[128],"We":[129],"extend":[130],"schemes":[132,156],"popular":[134],"evaluate":[138],"them":[139],"series":[142],"StarCraftII,":[144],"Google":[145],"Football":[146],"Multi-Agent":[148],"MuJoCo":[149],"tasks,":[150,164],"show":[152],"that":[153],"can":[157],"enhance":[158],"many":[163],"whatever":[165],"performance,":[167],"efficiency":[168],"or":[169],"stability,":[170],"indicating":[171],"its":[172],"modeling":[173],"capability":[174],"both":[176],"homogeneous":[177],"heterogeneous":[179],"tasks.":[181]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}