{"id":"https://openalex.org/W4226445221","doi":"https://doi.org/10.1631/fitee.2100594","title":"Coach-assisted multi-agent reinforcement learning framework for unexpected crashed agents","display_name":"Coach-assisted multi-agent reinforcement learning framework for unexpected crashed agents","publication_year":2022,"publication_date":"2022-07-01","ids":{"openalex":"https://openalex.org/W4226445221","doi":"https://doi.org/10.1631/fitee.2100594"},"language":"en","primary_location":{"id":"doi:10.1631/fitee.2100594","is_oa":false,"landing_page_url":"https://doi.org/10.1631/fitee.2100594","pdf_url":null,"source":{"id":"https://openalex.org/S4210189857","display_name":"Frontiers of Information Technology & Electronic Engineering","issn_l":"2095-9184","issn":["2095-9184","2095-9230"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers of Information Technology &amp; Electronic Engineering","raw_type":"journal-article"},"type":"article","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":null,"display_name":"Jian Zhao","orcid":"https://orcid.org/0000-0003-4895-990X"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Zhao","raw_affiliation_strings":["School of Information Science and Technology, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0003-4895-990X","affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008280430","display_name":"Yuxin Zhao","orcid":"https://orcid.org/0000-0003-4123-8480"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Youpeng Zhao","raw_affiliation_strings":["School of Information Science and Technology, University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082417441","display_name":"Weixun Wang","orcid":"https://orcid.org/0000-0002-2727-8948"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weixun Wang","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030078204","display_name":"Ming\u2010Yu Yang","orcid":"https://orcid.org/0000-0002-6841-5478"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingyu Yang","raw_affiliation_strings":["School of Information Science and Technology, University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044832538","display_name":"Xunhan Hu","orcid":"https://orcid.org/0000-0003-0239-3541"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xunhan Hu","raw_affiliation_strings":["School of Information Science and Technology, University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046805800","display_name":"Wengang Zhou","orcid":"https://orcid.org/0000-0003-1690-9836"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wengang Zhou","raw_affiliation_strings":["School of Information Science and Technology, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0003-1690-9836","affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047509839","display_name":"Jianye Hao","orcid":"https://orcid.org/0000-0002-0422-8235"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianye Hao","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078141810","display_name":"Houqiang Li","orcid":"https://orcid.org/0000-0003-2188-3028"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Houqiang Li","raw_affiliation_strings":["School of Information Science and Technology, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0003-2188-3028","affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2990,"currency":"USD","value_usd":2990},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.04061196,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"23","issue":"7","first_page":"1032","last_page":"1042"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.7454000115394592,"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":0.7454000115394592,"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/T10639","display_name":"Advanced Software Engineering Methodologies","score":0.0284000001847744,"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/T12127","display_name":"Software System Performance and Reliability","score":0.02370000071823597,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8734724521636963},{"id":"https://openalex.org/keywords/crash","display_name":"Crash","score":0.7344032526016235},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6940009593963623},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5665591359138489},{"id":"https://openalex.org/keywords/coaching","display_name":"Coaching","score":0.4739380180835724},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4133647680282593}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8734724521636963},{"id":"https://openalex.org/C183469790","wikidata":"https://www.wikidata.org/wiki/Q333501","display_name":"Crash","level":2,"score":0.7344032526016235},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6940009593963623},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5665591359138489},{"id":"https://openalex.org/C2779363792","wikidata":"https://www.wikidata.org/wiki/Q1104185","display_name":"Coaching","level":2,"score":0.4739380180835724},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4133647680282593},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1631/fitee.2100594","is_oa":false,"landing_page_url":"https://doi.org/10.1631/fitee.2100594","pdf_url":null,"source":{"id":"https://openalex.org/S4210189857","display_name":"Frontiers of Information Technology & Electronic Engineering","issn_l":"2095-9184","issn":["2095-9184","2095-9230"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers of Information Technology &amp; Electronic Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1518858799","https://openalex.org/W1641379095","https://openalex.org/W2099618002","https://openalex.org/W2110906765","https://openalex.org/W2145339207","https://openalex.org/W2158782408","https://openalex.org/W2166533447","https://openalex.org/W2292533394","https://openalex.org/W2465948386","https://openalex.org/W2605102758","https://openalex.org/W2615547864","https://openalex.org/W2981011740","https://openalex.org/W3045932801","https://openalex.org/W3088310808","https://openalex.org/W3090612618","https://openalex.org/W3166149430","https://openalex.org/W3176552354","https://openalex.org/W6600135713","https://openalex.org/W6600137863","https://openalex.org/W6600481524","https://openalex.org/W6687439459","https://openalex.org/W6776992756"],"related_works":["https://openalex.org/W700355","https://openalex.org/W1353223","https://openalex.org/W770098","https://openalex.org/W929682","https://openalex.org/W1238551","https://openalex.org/W868042","https://openalex.org/W1230437","https://openalex.org/W4412456","https://openalex.org/W547392","https://openalex.org/W1323832"],"abstract_inverted_index":{"Multi-agent":[0],"reinforcement":[1,83,103],"learning":[2,84,104,183],"is":[3,24,147],"difficult":[4],"to":[5,53,68,96,112,150],"apply":[6],"in":[7,39,154],"practice,":[8,40],"partially":[9],"because":[10],"of":[11,79,93,170,192],"the":[12,22,36,49,62,91,94,114,148,168,171,176,190],"gap":[13,23],"between":[14],"simulated":[15,26],"and":[16,66,130,134,162,181],"real-world":[17],"scenarios.":[18],"One":[19],"reason":[20],"for":[21,138],"that":[25,30,106],"systems":[27],"always":[28],"assume":[29],"agents":[31,44,65],"can":[32],"work":[33,146],"normally":[34],"all":[35],"time,":[37],"while":[38],"one":[41],"or":[42,56],"more":[43],"may":[45],"unexpectedly":[46],"\u201ccrash\u201d":[47],"during":[48,117],"coordination":[50],"process":[51],"due":[52],"inevitable":[54],"hardware":[55],"software":[57],"failures.":[58],"Such":[59],"crashes":[60,153],"destroy":[61],"cooperation":[63],"among":[64],"lead":[67],"performance":[69],"degradation.":[70],"In":[71],"this":[72,145],"work,":[73],"we":[74,98],"present":[75],"a":[76,80,100,108,135,155],"formal":[77],"conceptualization":[78],"cooperative":[81],"multi-agent":[82,102,156],"system":[85,95],"with":[86,175],"unexpected":[87,152],"crashes.":[88],"To":[89,142],"enhance":[90],"robustness":[92],"crashes,":[97],"propose":[99],"coach-assisted":[101],"framework":[105],"introduces":[107],"virtual":[109],"coach":[110,140],"agent":[111],"adjust":[113],"crash":[115,126,132,178],"rate":[116,179],"training.":[118],"We":[119],"have":[120],"designed":[121],"three":[122],"coaching":[123],"strategies":[124],"(fixed":[125],"rate,":[127],"curriculum":[128,182],"learning,":[129],"adaptive":[131,172],"rate)":[133],"re-sampling":[136,194],"strategy":[137,173,180],"our":[139,143,193],"agent.":[141],"knowledge,":[144],"first":[149],"study":[151,187],"system.":[157],"Extensive":[158],"experiments":[159],"on":[160],"grid-world":[161],"StarCraft":[163],"II":[164],"micromanagement":[165],"tasks":[166],"demonstrate":[167],"efficacy":[169],"compared":[174],"fixed":[177],"strategy.":[184,195],"The":[185],"ablation":[186],"further":[188],"illustrates":[189],"effectiveness":[191]},"counts_by_year":[],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2022-05-05T00:00:00"}
