{"id":"https://openalex.org/W3097100992","doi":"https://doi.org/10.1109/icnsc48988.2020.9238072","title":"A Coordinated Multiagent Reinforcement Learning Method Using Chicken Game","display_name":"A Coordinated Multiagent Reinforcement Learning Method Using Chicken Game","publication_year":2020,"publication_date":"2020-10-30","ids":{"openalex":"https://openalex.org/W3097100992","doi":"https://doi.org/10.1109/icnsc48988.2020.9238072","mag":"3097100992"},"language":"en","primary_location":{"id":"doi:10.1109/icnsc48988.2020.9238072","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icnsc48988.2020.9238072","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Networking, Sensing and Control (ICNSC)","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/A5100712588","display_name":"Zihui Wang","orcid":"https://orcid.org/0000-0002-2512-7361"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zihui Wang","raw_affiliation_strings":["Nanjing University, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100376415","display_name":"Zhi Wang","orcid":"https://orcid.org/0000-0003-0304-3965"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhi Wang","raw_affiliation_strings":["Nanjing University, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100697167","display_name":"Chunlin Chen","orcid":"https://orcid.org/0000-0003-3929-4707"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunlin Chen","raw_affiliation_strings":["Nanjing University, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I881766915"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.989799976348877,"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":0.9871000051498413,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8352473974227905},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7166857123374939},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6900589466094971},{"id":"https://openalex.org/keywords/nash-equilibrium","display_name":"Nash equilibrium","score":0.6598843336105347},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5453781485557556},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5177909135818481},{"id":"https://openalex.org/keywords/marl","display_name":"Marl","score":0.5108225345611572},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.4476163983345032},{"id":"https://openalex.org/keywords/game-theory","display_name":"Game theory","score":0.4246233105659485},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34441179037094116},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2050153613090515},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17119145393371582},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.09820935130119324}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8352473974227905},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7166857123374939},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6900589466094971},{"id":"https://openalex.org/C46814582","wikidata":"https://www.wikidata.org/wiki/Q23389","display_name":"Nash equilibrium","level":2,"score":0.6598843336105347},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5453781485557556},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5177909135818481},{"id":"https://openalex.org/C92927620","wikidata":"https://www.wikidata.org/wiki/Q184053","display_name":"Marl","level":3,"score":0.5108225345611572},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.4476163983345032},{"id":"https://openalex.org/C177142836","wikidata":"https://www.wikidata.org/wiki/Q44455","display_name":"Game theory","level":2,"score":0.4246233105659485},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34441179037094116},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2050153613090515},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17119145393371582},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.09820935130119324},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C109007969","wikidata":"https://www.wikidata.org/wiki/Q749565","display_name":"Structural basin","level":2,"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},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icnsc48988.2020.9238072","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icnsc48988.2020.9238072","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Networking, Sensing and Control (ICNSC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2172947564","display_name":"\u5927\u6570\u636e\u80cc\u666f\u4e0b\u7684\u9879\u76ee\u7ba1\u7406\u7406\u8bba\u4e0e\u6a21\u5f0f\u7814\u7a76","funder_award_id":"71732003","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G801081501","display_name":null,"funder_award_id":"011814380035","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W11035765","https://openalex.org/W32403112","https://openalex.org/W1542941925","https://openalex.org/W1564534945","https://openalex.org/W2036103676","https://openalex.org/W2054339854","https://openalex.org/W2064217014","https://openalex.org/W2070963703","https://openalex.org/W2097381042","https://openalex.org/W2099618002","https://openalex.org/W2120846115","https://openalex.org/W2128814508","https://openalex.org/W2153427071","https://openalex.org/W2160041839","https://openalex.org/W2259258048","https://openalex.org/W2338351427","https://openalex.org/W2519634894","https://openalex.org/W2559014014","https://openalex.org/W2589844156","https://openalex.org/W2912681837","https://openalex.org/W3036721391","https://openalex.org/W6600453709","https://openalex.org/W6632558091","https://openalex.org/W6678168664","https://openalex.org/W6682999179","https://openalex.org/W6729855137"],"related_works":["https://openalex.org/W2742483371","https://openalex.org/W3096874164","https://openalex.org/W2166117066","https://openalex.org/W3087814763","https://openalex.org/W2357975469","https://openalex.org/W2136202932","https://openalex.org/W4376605461","https://openalex.org/W4400868993","https://openalex.org/W2361647908","https://openalex.org/W2952356279"],"abstract_inverted_index":{"Sparse":[0,55],"interaction":[1,61],"in":[2,87],"multiagent":[3,16],"tasks":[4],"is":[5,27],"an":[6,64],"important":[7],"approach":[8],"to":[9,22,30,36,96,113,128],"reduce":[10],"the":[11,28,32,38,59,83,115,121],"exponential":[12],"computational":[13],"cost":[14],"for":[15],"reinforcement":[17],"learning":[18,39],"(MARL)":[19],"systems.":[20],"How":[21],"select":[23],"proper":[24],"equilibrium":[25,69,75,111],"solutions":[26,70,112],"key":[29],"find":[31,114],"optimal":[33,116],"policy":[34],"and":[35,63,76,100,123],"improve":[37],"performance":[40],"when":[41],"collisions":[42],"occur.":[43],"We":[44],"propose":[45],"a":[46],"new":[47],"MARL":[48,53,131],"algorithm,":[49],"Efficient":[50],"Coordination":[51],"based":[52],"with":[54,93,110],"Interactions":[56],"(ECoSI),":[57],"using":[58],"sparse":[60,94],"framework":[62],"efficient":[65,108],"coordination":[66,109],"mechanism,":[67],"where":[68],"are":[71],"selected":[72],"via":[73],"Nash":[74],"Chicken":[77],"game.":[78],"ECoSI":[79,126],"not":[80],"only":[81],"separates":[82],"Q-value":[84],"updating":[85],"rule":[86],"joint":[88],"states":[89,92],"from":[90],"non-joint":[91],"interactions":[95],"achieve":[97],"lower":[98],"computation":[99],"storage":[101],"complexity,":[102],"but":[103],"also":[104],"takes":[105],"advantage":[106],"of":[107,125],"policy.":[117],"Experimental":[118],"results":[119],"demonstrate":[120],"effectiveness":[122],"robustness":[124],"compared":[127],"other":[129],"state-of-the-art":[130],"algorithms.":[132]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}