{"id":"https://openalex.org/W4320027845","doi":"https://doi.org/10.1109/robio55434.2022.10011827","title":"Multi-Robot Real-time Game Strategy Learning based on Deep Reinforcement Learning","display_name":"Multi-Robot Real-time Game Strategy Learning based on Deep Reinforcement Learning","publication_year":2022,"publication_date":"2022-12-05","ids":{"openalex":"https://openalex.org/W4320027845","doi":"https://doi.org/10.1109/robio55434.2022.10011827"},"language":"en","primary_location":{"id":"doi:10.1109/robio55434.2022.10011827","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/robio55434.2022.10011827","pdf_url":null,"source":{"id":"https://openalex.org/S4363607789","display_name":"2022 IEEE International Conference on Robotics and Biomimetics (ROBIO)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 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/A5046569117","display_name":"Ki Deng","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"]},{"id":"https://openalex.org/I158809036","display_name":"Shenzhen Institute of Information Technology","ror":"https://ror.org/03wrf9427","country_code":"CN","type":"education","lineage":["https://openalex.org/I158809036"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ki Deng","raw_affiliation_strings":["Harbin Institute of Technology, Shenzhen,Department of Control Science and Engineering,Shenzhen,China","Department of Control Science and Engineering, Harbin Institute of Technology, Shenzhen, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Shenzhen,Department of Control Science and Engineering,Shenzhen,China","institution_ids":["https://openalex.org/I158809036","https://openalex.org/I204983213"]},{"raw_affiliation_string":"Department of Control Science and Engineering, Harbin Institute of Technology, Shenzhen, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100677178","display_name":"Yanjie Li","orcid":"https://orcid.org/0000-0001-7890-9677"},"institutions":[{"id":"https://openalex.org/I158809036","display_name":"Shenzhen Institute of Information Technology","ror":"https://ror.org/03wrf9427","country_code":"CN","type":"education","lineage":["https://openalex.org/I158809036"]},{"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":"Yanjie Li","raw_affiliation_strings":["Harbin Institute of Technology, Shenzhen,Department of Control Science and Engineering,Shenzhen,China","Department of Control Science and Engineering, Harbin Institute of Technology, Shenzhen, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Shenzhen,Department of Control Science and Engineering,Shenzhen,China","institution_ids":["https://openalex.org/I158809036","https://openalex.org/I204983213"]},{"raw_affiliation_string":"Department of Control Science and Engineering, Harbin Institute of Technology, Shenzhen, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082396199","display_name":"Songshuo Lu","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"]},{"id":"https://openalex.org/I158809036","display_name":"Shenzhen Institute of Information Technology","ror":"https://ror.org/03wrf9427","country_code":"CN","type":"education","lineage":["https://openalex.org/I158809036"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Songshuo Lu","raw_affiliation_strings":["Harbin Institute of Technology, Shenzhen,Department of Control Science and Engineering,Shenzhen,China","Department of Control Science and Engineering, Harbin Institute of Technology, Shenzhen, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Shenzhen,Department of Control Science and Engineering,Shenzhen,China","institution_ids":["https://openalex.org/I158809036","https://openalex.org/I204983213"]},{"raw_affiliation_string":"Department of Control Science and Engineering, Harbin Institute of Technology, Shenzhen, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085521136","display_name":"Yongjin Mu","orcid":null},"institutions":[{"id":"https://openalex.org/I158809036","display_name":"Shenzhen Institute of Information Technology","ror":"https://ror.org/03wrf9427","country_code":"CN","type":"education","lineage":["https://openalex.org/I158809036"]},{"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":"Yongjin Mu","raw_affiliation_strings":["Harbin Institute of Technology, Shenzhen,Department of Control Science and Engineering,Shenzhen,China","Department of Control Science and Engineering, Harbin Institute of Technology, Shenzhen, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Shenzhen,Department of Control Science and Engineering,Shenzhen,China","institution_ids":["https://openalex.org/I158809036","https://openalex.org/I204983213"]},{"raw_affiliation_string":"Department of Control Science and Engineering, Harbin Institute of Technology, Shenzhen, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047707212","display_name":"Xizheng Pang","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"]},{"id":"https://openalex.org/I158809036","display_name":"Shenzhen Institute of Information Technology","ror":"https://ror.org/03wrf9427","country_code":"CN","type":"education","lineage":["https://openalex.org/I158809036"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xizheng Pang","raw_affiliation_strings":["Harbin Institute of Technology, Shenzhen,Department of Control Science and Engineering,Shenzhen,China","Department of Control Science and Engineering, Harbin Institute of Technology, Shenzhen, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Shenzhen,Department of Control Science and Engineering,Shenzhen,China","institution_ids":["https://openalex.org/I158809036","https://openalex.org/I204983213"]},{"raw_affiliation_string":"Department of Control Science and Engineering, Harbin Institute of Technology, Shenzhen, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100453159","display_name":"Qi Liu","orcid":"https://orcid.org/0000-0001-7485-6344"},"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"]},{"id":"https://openalex.org/I158809036","display_name":"Shenzhen Institute of Information Technology","ror":"https://ror.org/03wrf9427","country_code":"CN","type":"education","lineage":["https://openalex.org/I158809036"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Liu","raw_affiliation_strings":["Harbin Institute of Technology, Shenzhen,Department of Control Science and Engineering,Shenzhen,China","Department of Control Science and Engineering, Harbin Institute of Technology, Shenzhen, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Shenzhen,Department of Control Science and Engineering,Shenzhen,China","institution_ids":["https://openalex.org/I158809036","https://openalex.org/I204983213"]},{"raw_affiliation_string":"Department of Control Science and Engineering, Harbin Institute of Technology, Shenzhen, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5046569117"],"corresponding_institution_ids":["https://openalex.org/I158809036","https://openalex.org/I204983213"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.20701357,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"11","issue":null,"first_page":"1192","last_page":"1197"},"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/T11574","display_name":"Artificial Intelligence in Games","score":0.9837999939918518,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9758999943733215,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8978511095046997},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.7497251629829407},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6995523571968079},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6216299533843994},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5346803665161133},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.491489052772522},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.3322156071662903}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8978511095046997},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.7497251629829407},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6995523571968079},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6216299533843994},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5346803665161133},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.491489052772522},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.3322156071662903},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","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/robio55434.2022.10011827","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/robio55434.2022.10011827","pdf_url":null,"source":{"id":"https://openalex.org/S4363607789","display_name":"2022 IEEE International Conference on Robotics and Biomimetics (ROBIO)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Robotics and Biomimetics (ROBIO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.5400000214576721}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1882451095","https://openalex.org/W1976195538","https://openalex.org/W2145339207","https://openalex.org/W2153073482","https://openalex.org/W2156737235","https://openalex.org/W2257979135","https://openalex.org/W2626637010","https://openalex.org/W2736601468","https://openalex.org/W2786344118","https://openalex.org/W2786928559","https://openalex.org/W2905191592","https://openalex.org/W2981171231","https://openalex.org/W2982316857","https://openalex.org/W2996037775","https://openalex.org/W2998655286","https://openalex.org/W3001500272","https://openalex.org/W3107615218","https://openalex.org/W3113104257","https://openalex.org/W3127332340","https://openalex.org/W4226383439","https://openalex.org/W4230168121","https://openalex.org/W4286748781","https://openalex.org/W4299802797","https://openalex.org/W6683195989","https://openalex.org/W6684205842","https://openalex.org/W6689723076","https://openalex.org/W6738796088","https://openalex.org/W6739516088","https://openalex.org/W6741002519","https://openalex.org/W6747473740","https://openalex.org/W6748554570","https://openalex.org/W6749304979","https://openalex.org/W6757156986","https://openalex.org/W6772005887","https://openalex.org/W6786364697","https://openalex.org/W6840380725"],"related_works":["https://openalex.org/W2122871747","https://openalex.org/W3114279067","https://openalex.org/W2930863966","https://openalex.org/W2126211886","https://openalex.org/W3153786280","https://openalex.org/W3127551068","https://openalex.org/W4220829754","https://openalex.org/W2165180011","https://openalex.org/W3165944253","https://openalex.org/W2351343564"],"abstract_inverted_index":{"With":[0],"the":[1,7,13,21,44,50,58,69,87,92,98,116,119],"booming":[2],"development":[3],"of":[4,10,23,46,61,72,118],"artificial":[5,62],"in-telligence,":[6],"autonomous":[8],"decision-making":[9,35],"robots":[11],"on":[12,57,115],"battlefield":[14],"has":[15,128],"become":[16],"a":[17,78,129],"future":[18],"trend.":[19],"In":[20,75,111],"field":[22,45],"en-tertainment":[24],"games,":[25],"some":[26],"institutions":[27],"have":[28],"already":[29],"attained":[30],"outstanding":[31],"results":[32],"in":[33,43,64],"multi-agent":[34,105],"tasks":[36],"by":[37,101],"using":[38],"reinforcement":[39,93],"learning":[40,94],"algorithms.":[41],"But":[42],"robot":[47,51,73],"confrontation":[48,52],"game,":[49],"strategies":[53],"are":[54],"still":[55],"based":[56,114],"simple":[59],"logic":[60],"design":[63],"most":[65],"cases,":[66],"which":[67],"hinders":[68],"further":[70],"improvement":[71],"strategies.":[74],"this":[76],"paper,":[77],"reinforcement-learning-based":[79],"multi-robot":[80],"control":[81],"method":[82,100,127],"is":[83],"proposed":[84],"to":[85],"improve":[86,108],"strategy":[88],"performance.":[89],"We":[90],"enhanced":[91],"algorithm":[95],"PPO":[96],"with":[97],"self-play":[99],"easy-to-implement":[102],"tricks":[103],"for":[104],"training":[106,109],"and":[107],"efficiency.":[110],"simulated":[112],"experiments":[113],"rules":[117],"RoboMaster":[120],"University":[121],"AI":[122],"Challenge,":[123],"we":[124],"show":[125],"our":[126],"much":[130],"higher":[131],"winning":[132],"percentage":[133],"than":[134],"traditional":[135],"approaches":[136],"like":[137],"behavior":[138],"tree.":[139]},"counts_by_year":[],"updated_date":"2025-12-23T23:11:35.936235","created_date":"2025-10-10T00:00:00"}