{"id":"https://openalex.org/W2965153080","doi":"https://doi.org/10.24963/ijcai.2019/51","title":"Explicitly Coordinated Policy Iteration","display_name":"Explicitly Coordinated Policy Iteration","publication_year":2019,"publication_date":"2019-07-28","ids":{"openalex":"https://openalex.org/W2965153080","doi":"https://doi.org/10.24963/ijcai.2019/51","mag":"2965153080"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2019/51","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/51","pdf_url":"https://www.ijcai.org/proceedings/2019/0051.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2019/0051.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5104264364","display_name":"Yujing Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yujing Hu","raw_affiliation_strings":["Fuxi AI Lab in Netease"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fuxi AI Lab in Netease","institution_ids":["https://openalex.org/I4210091137"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103121632","display_name":"Yingfeng Chen","orcid":"https://orcid.org/0000-0002-9747-5947"},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingfeng Chen","raw_affiliation_strings":["Fuxi AI Lab in Netease"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fuxi AI Lab in Netease","institution_ids":["https://openalex.org/I4210091137"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022008180","display_name":"Changjie Fan","orcid":"https://orcid.org/0000-0001-5420-0516"},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changjie Fan","raw_affiliation_strings":["Fuxi AI Lab in Netease"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fuxi AI Lab in Netease","institution_ids":["https://openalex.org/I4210091137"]}]},{"author_position":"last","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":["Tianjin University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University","institution_ids":["https://openalex.org/I162868743"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"357","last_page":"363"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":1.0,"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":1.0,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9983000159263611,"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"}},{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9761000275611877,"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":0.7603014707565308},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.7307828664779663},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6378176212310791},{"id":"https://openalex.org/keywords/coordination-game","display_name":"Coordination game","score":0.6334186792373657},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5325497388839722},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4711412787437439},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4416612386703491},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4243805408477783},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3067508935928345},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.2499934732913971},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2453702688217163},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13660413026809692}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7603014707565308},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.7307828664779663},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6378176212310791},{"id":"https://openalex.org/C107257861","wikidata":"https://www.wikidata.org/wiki/Q656316","display_name":"Coordination game","level":2,"score":0.6334186792373657},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5325497388839722},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4711412787437439},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4416612386703491},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4243805408477783},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3067508935928345},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.2499934732913971},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2453702688217163},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13660413026809692},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2019/51","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/51","pdf_url":"https://www.ijcai.org/proceedings/2019/0051.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2019/51","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/51","pdf_url":"https://www.ijcai.org/proceedings/2019/0051.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8462351438","display_name":null,"funder_award_id":"61702362","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8921145797","display_name":null,"funder_award_id":"U1836214","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2965153080.pdf","grobid_xml":"https://content.openalex.org/works/W2965153080.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W178386168","https://openalex.org/W1542941925","https://openalex.org/W1560074431","https://openalex.org/W1641379095","https://openalex.org/W2085366587","https://openalex.org/W2096145798","https://openalex.org/W2099618002","https://openalex.org/W2103561211","https://openalex.org/W2104602264","https://openalex.org/W2108449787","https://openalex.org/W2108892923","https://openalex.org/W2120327309","https://openalex.org/W2120846115","https://openalex.org/W2129936995","https://openalex.org/W2145339207","https://openalex.org/W2164637474","https://openalex.org/W2466211196","https://openalex.org/W2617547828","https://openalex.org/W2730807149","https://openalex.org/W2734878594","https://openalex.org/W2951896791","https://openalex.org/W4299802797"],"related_works":["https://openalex.org/W2280422768","https://openalex.org/W3143197806","https://openalex.org/W4252555497","https://openalex.org/W3121175838","https://openalex.org/W3016293053","https://openalex.org/W1690653314","https://openalex.org/W2401723157","https://openalex.org/W2065055572","https://openalex.org/W2784269775","https://openalex.org/W2952904874"],"abstract_inverted_index":{"Coordination":[0],"on":[1,30,83],"an":[2,63,88],"optimal":[3,80,89],"policy":[4,96],"between":[5,39],"independent":[6],"learners":[7],"in":[8,56,76,130],"fully":[9],"cooperative":[10],"stochastic":[11,142],"games":[12,132,136,143,146],"is":[13],"difficult":[14],"due":[15],"to":[16,70,104,137,147],"problems":[17,77],"such":[18,46,52],"as":[19,53,161],"relative":[20],"overgeneralization":[21],"and":[22,33,112,141,164],"miscoordination.":[23],"Most":[24],"state-of-the-art":[25,158],"algorithms":[26,159],"apply":[27],"fusion":[28],"heuristics":[29],"agents'":[31,109],"optimistic":[32,111],"average":[34,113],"rewards,":[35],"by":[36,106],"which":[37,100],"coordination":[38,48,65,75],"agents":[40,103],"can":[41],"be":[42],"achieved":[43],"implicitly.":[44],"However,":[45],"implicit":[47],"faces":[49],"practical":[50],"issues":[51],"tedious":[54],"parameter-tuning":[55],"real":[57],"world":[58],"applications.":[59],"The":[60],"lack":[61],"of":[62,74,87,126],"explicit":[64],"mechanism":[66],"may":[67],"also":[68,117],"lead":[69],"a":[71],"low":[72],"likelihood":[73],"with":[78],"multiple":[79],"policies.":[81],"Based":[82],"the":[84,93,108,157],"necessary":[85],"conditions":[86],"policy,":[90],"we":[91],"propose":[92,118],"explicitly":[94],"coordinated":[95],"iteration":[97],"(EXCEL)":[98],"algorithm":[99],"always":[101],"forces":[102],"coordinate":[105],"comparing":[107],"separated":[110],"value":[114],"functions.":[115],"We":[116],"three":[119],"solutions":[120],"for":[121],"deep":[122],"reinforcement":[123],"learning":[124],"extensions":[125],"EXCEL.":[127],"Extensive":[128],"experiments":[129],"matrix":[131],"(from":[133,144],"2-agent":[134,145],"2-action":[135],"5-agent":[138,148],"20-action":[139],"games)":[140,149],"show":[150],"that":[151],"EXCEL":[152],"has":[153],"better":[154,165],"performance":[155],"than":[156],"(such":[160],"faster":[162],"convergence":[163],"coordination).":[166]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}