{"id":"https://openalex.org/W2921522287","doi":"https://doi.org/10.1109/robio.2018.8665165","title":"Multi-Robot Cooperation Strategy in Game Environment Using Deep Reinforcement Learning","display_name":"Multi-Robot Cooperation Strategy in Game Environment Using Deep Reinforcement Learning","publication_year":2018,"publication_date":"2018-12-01","ids":{"openalex":"https://openalex.org/W2921522287","doi":"https://doi.org/10.1109/robio.2018.8665165","mag":"2921522287"},"language":"en","primary_location":{"id":"doi:10.1109/robio.2018.8665165","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robio.2018.8665165","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Robotics and Biomimetics (ROBIO)","raw_type":"proceedings-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":"https://openalex.org/A5101680982","display_name":"Hongda Zhang","orcid":"https://orcid.org/0000-0002-2109-5972"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hongda Zhang","raw_affiliation_strings":["The University of Chinese Academy of Sciences, Bejing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Chinese Academy of Sciences, Bejing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101773900","display_name":"Decai Li","orcid":"https://orcid.org/0000-0003-4140-3861"},"institutions":[{"id":"https://openalex.org/I142078773","display_name":"Shenyang Institute of Automation","ror":"https://ror.org/00ft6nj33","country_code":"CN","type":"facility","lineage":["https://openalex.org/I142078773","https://openalex.org/I19820366"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Decai Li","raw_affiliation_strings":["Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang, China","institution_ids":["https://openalex.org/I142078773","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100654736","display_name":"Yuqing He","orcid":"https://orcid.org/0000-0001-5067-1169"},"institutions":[{"id":"https://openalex.org/I142078773","display_name":"Shenyang Institute of Automation","ror":"https://ror.org/00ft6nj33","country_code":"CN","type":"facility","lineage":["https://openalex.org/I142078773","https://openalex.org/I19820366"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuqing He","raw_affiliation_strings":["Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang, China","institution_ids":["https://openalex.org/I142078773","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101680982"],"corresponding_institution_ids":["https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":0.5081,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.75674434,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"529","issue":null,"first_page":"886","last_page":"891"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.9631999731063843,"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":0.9448000192642212,"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":0.8847531080245972},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6911346912384033},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6754776239395142},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5587302446365356},{"id":"https://openalex.org/keywords/nash-equilibrium","display_name":"Nash equilibrium","score":0.4783689081668854},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.43215349316596985},{"id":"https://openalex.org/keywords/game-theory","display_name":"Game theory","score":0.4179675579071045},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.33269524574279785},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.2907930016517639},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.08332681655883789}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8847531080245972},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6911346912384033},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6754776239395142},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5587302446365356},{"id":"https://openalex.org/C46814582","wikidata":"https://www.wikidata.org/wiki/Q23389","display_name":"Nash equilibrium","level":2,"score":0.4783689081668854},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.43215349316596985},{"id":"https://openalex.org/C177142836","wikidata":"https://www.wikidata.org/wiki/Q44455","display_name":"Game theory","level":2,"score":0.4179675579071045},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.33269524574279785},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.2907930016517639},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.08332681655883789},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C175444787","wikidata":"https://www.wikidata.org/wiki/Q39072","display_name":"Microeconomics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/robio.2018.8665165","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robio.2018.8665165","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Robotics and Biomimetics (ROBIO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.5799999833106995}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1757796397","https://openalex.org/W1979239334","https://openalex.org/W2145339207","https://openalex.org/W2257979135","https://openalex.org/W2518713116","https://openalex.org/W2592798481","https://openalex.org/W2604283518","https://openalex.org/W2735263551","https://openalex.org/W2749807327","https://openalex.org/W2810602713","https://openalex.org/W2962887844","https://openalex.org/W2962938168","https://openalex.org/W2963179910","https://openalex.org/W2963937357","https://openalex.org/W2964338167","https://openalex.org/W4293862243","https://openalex.org/W4298857966","https://openalex.org/W6637967152","https://openalex.org/W6645151609","https://openalex.org/W6734678876"],"related_works":["https://openalex.org/W2930863966","https://openalex.org/W4312141693","https://openalex.org/W1536009559","https://openalex.org/W2126211886","https://openalex.org/W2103821767","https://openalex.org/W1969185016","https://openalex.org/W3153786280","https://openalex.org/W2037619003","https://openalex.org/W2111030377","https://openalex.org/W3127551068"],"abstract_inverted_index":{"The":[0,48],"multi-robot":[1,35,73,157,170],"system":[2,158,171],"combines":[3],"the":[4,16,25,28,32,38,56,69,80,87,92,120,134,145,155,162],"characteristics":[5],"and":[6,12,95,143,160],"advantages":[7],"of":[8,18,27,40,51,147,164],"each":[9],"component":[10],"robot":[11],"can":[13,101],"break":[14],"through":[15],"constraints":[17],"a":[19,65,97,113],"single":[20],"robot's":[21],"capability,":[22],"greatly":[23],"expanding":[24],"application":[26],"robot.":[29],"However,":[30],"in":[31,43,55,91,168],"game":[33,57,93,116,123],"environment,":[34],"systems":[36],"face":[37],"challenge":[39],"intelligent":[41],"decision-making":[42,53],"high-dimensional":[44],"complex":[45],"dynamic":[46],"environments.":[47],"research":[49],"progress":[50],"multi-agent":[52,88,122,165],"strategies":[54],"environment":[58,94],"based":[59,78,172],"on":[60,79,119,154,173],"deep":[61,81,128,174],"reinforcement":[62,82,175],"learning":[63,83,98,130],"provides":[64],"solution":[66],"for":[67],"solving":[68],"problems":[70],"faced":[71],"by":[72],"systems.":[74],"To":[75],"this":[76,109],"end,":[77],"method,":[84],"we":[85,111,151],"analyze":[86],"collaboration":[89],"strategy":[90,117,167],"propose":[96],"method":[99,131],"that":[100],"measure":[102],"cooperative":[103],"information":[104],"between":[105],"multiple":[106],"agents.":[107],"On":[108],"basis,":[110],"conduct":[112],"Nash":[114],"equilibrium":[115],"analysis":[118],"specific":[121],"problem-the":[124],"territory":[125],"defense,":[126],"use":[127],"Q":[129],"to":[132],"learn":[133],"defender's":[135],"joint":[136],"defense":[137],"strategy.":[138],"We":[139],"conducted":[140,152],"simulation":[141],"experiments":[142,153],"verified":[144],"effectiveness":[146],"our":[148],"method.":[149],"Furthermore,":[150],"actual":[156],"platform":[159],"demonstrated":[161],"feasibility":[163],"cooperation":[166],"practical":[169],"learning.":[176]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2026-05-02T08:42:23.175194","created_date":"2025-10-10T00:00:00"}