{"id":"https://openalex.org/W4296474697","doi":"https://doi.org/10.1109/cog51982.2022.9893608","title":"Mastering the Game of 3v3 Snakes with Rule-Enhanced Multi-Agent Reinforcement Learning","display_name":"Mastering the Game of 3v3 Snakes with Rule-Enhanced Multi-Agent Reinforcement Learning","publication_year":2022,"publication_date":"2022-08-21","ids":{"openalex":"https://openalex.org/W4296474697","doi":"https://doi.org/10.1109/cog51982.2022.9893608"},"language":"en","primary_location":{"id":"doi:10.1109/cog51982.2022.9893608","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cog51982.2022.9893608","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Conference on Games (CoG)","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/A5101409697","display_name":"Jitao Wang","orcid":"https://orcid.org/0000-0002-3071-494X"},"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":true,"raw_author_name":"Jitao Wang","raw_affiliation_strings":["University of Science and Technology of China,Hefei,China","University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,Hefei,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018950191","display_name":"Dongyun Xue","orcid":"https://orcid.org/0000-0002-6985-7163"},"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":"Dongyun Xue","raw_affiliation_strings":["University of Science and Technology of China,Hefei,China","University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,Hefei,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046073205","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":["University of Science and Technology of China,Hefei,China","University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,Hefei,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"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/I4210137491","display_name":"National Science Center","ror":"https://ror.org/03ha2q922","country_code":"PL","type":"funder","lineage":["https://openalex.org/I4210137491"]},{"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","PL"],"is_corresponding":false,"raw_author_name":"Wengang Zhou","raw_affiliation_strings":["University of Science and Technology of China,Institute of Artificial Intelligence Hefei Comprehensive Nation Science Center,Hefei,China","Institute of Artificial Intelligence Hefei Comprehensive Nation Science Center, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,Institute of Artificial Intelligence Hefei Comprehensive Nation Science Center,Hefei,China","institution_ids":["https://openalex.org/I4210137491"]},{"raw_affiliation_string":"Institute of Artificial Intelligence Hefei Comprehensive Nation Science Center, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"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"]},{"id":"https://openalex.org/I4210137491","display_name":"National Science Center","ror":"https://ror.org/03ha2q922","country_code":"PL","type":"funder","lineage":["https://openalex.org/I4210137491"]}],"countries":["CN","PL"],"is_corresponding":false,"raw_author_name":"Houqiang Li","raw_affiliation_strings":["University of Science and Technology of China,Institute of Artificial Intelligence Hefei Comprehensive Nation Science Center,Hefei,China","Institute of Artificial Intelligence Hefei Comprehensive Nation Science Center, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,Institute of Artificial Intelligence Hefei Comprehensive Nation Science Center,Hefei,China","institution_ids":["https://openalex.org/I4210137491"]},{"raw_affiliation_string":"Institute of Artificial Intelligence Hefei Comprehensive Nation Science Center, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101409697"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.3979,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.66937395,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"229","last_page":"236"},"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":0.9968000054359436,"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":0.9959999918937683,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8128675222396851},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.657734215259552},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.6017080545425415},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3811055123806},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3523874282836914},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1659497320652008},{"id":"https://openalex.org/keywords/structural-engineering","display_name":"Structural engineering","score":0.11159297823905945}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8128675222396851},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.657734215259552},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.6017080545425415},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3811055123806},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3523874282836914},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1659497320652008},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.11159297823905945}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cog51982.2022.9893608","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cog51982.2022.9893608","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Conference on Games (CoG)","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":0.6100000143051147}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335892","display_name":"Youth Innovation Promotion Association","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W41554520","https://openalex.org/W1191599655","https://openalex.org/W1771410628","https://openalex.org/W2145339207","https://openalex.org/W2257979135","https://openalex.org/W2726187156","https://openalex.org/W2736601468","https://openalex.org/W2761873684","https://openalex.org/W2889665471","https://openalex.org/W2960876848","https://openalex.org/W2963864421","https://openalex.org/W2982316857","https://openalex.org/W2996037775","https://openalex.org/W2996896271","https://openalex.org/W3013828496","https://openalex.org/W3018569081","https://openalex.org/W3033081583","https://openalex.org/W3034087440","https://openalex.org/W3094607870","https://openalex.org/W3174676553","https://openalex.org/W4288594419","https://openalex.org/W6627932998","https://openalex.org/W6638018090","https://openalex.org/W6684921986","https://openalex.org/W6740222838","https://openalex.org/W6741002519","https://openalex.org/W6758846586","https://openalex.org/W6772005887","https://openalex.org/W6775289199","https://openalex.org/W6784682557"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588"],"abstract_inverted_index":{"As":[0],"a":[1,28,72,80,129],"popular":[2],"game":[3],"around":[4],"the":[5,21,63,87,99,104,153,160],"world,":[6],"Snakes":[7,82],"has":[8],"multiple":[9],"modes":[10],"with":[11,123],"different":[12],"settings.":[13],"In":[14],"this":[15,37],"work,":[16],"we":[17,70,85],"are":[18,116],"dedicated":[19],"to":[20,54,98],"3v3":[22,81],"Snakes,":[23,40],"which":[24,49,90],"is":[25,91],"characterized":[26],"by":[27,62],"complex":[29],"mixture":[30],"of":[31,39,57,65,112],"competition":[32],"and":[33,78,102,114,126,143,158],"cooperation.":[34],"To":[35],"address":[36],"mode":[38],"most":[41],"existing":[42],"AI":[43,139],"agents":[44,157],"adopt":[45],"rule":[46,95],"based":[47,96],"methods,":[48],"achieve":[50],"limited":[51],"performance":[52,142],"due":[53],"human\u2019s":[55],"oversight":[56],"some":[58],"special":[59],"circumstances.":[60],"Inspired":[61],"superiority":[64],"multi-agent":[66,74],"reinforcement":[67,75],"learning":[68,76],"(MARL),":[69],"propose":[71],"rule-enhanced":[73],"algorithm":[77],"build":[79],"AI.":[83],"Specifically,":[84],"introduce":[86],"territory":[88],"matrix":[89],"commonly":[92],"utilized":[93],"in":[94],"methods":[97],"state":[100],"features":[101],"mask":[103],"illegal":[105],"actions":[106],"through":[107],"designed":[108],"rules.":[109],"The":[110],"relationships":[111],"individual-team":[113],"friends-foes":[115],"also":[117],"merged":[118],"into":[119],"reward":[120],"design.":[121],"Trained":[122],"Distributed":[124],"PPO":[125],"self-play":[127],"on":[128],"single":[130],"GeForce":[131],"RTX":[132],"2080":[133],"GPU":[134],"for":[135,162],"twenty-four":[136],"hours,":[137],"our":[138,150],"achieves":[140],"state-of-the-art":[141],"beats":[144],"human":[145],"players.":[146],"On":[147],"JIDI":[148],"platform,":[149],"agent":[151],"outperforms":[152],"other":[154],"132":[155],"participating":[156],"ranks":[159],"first":[161],"more":[163],"than":[164],"20":[165],"consecutive":[166],"days.":[167]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}