{"id":"https://openalex.org/W2946025546","doi":null,"title":"Grid-Wise Control for Multi-Agent Reinforcement Learning in Video Game AI.","display_name":"Grid-Wise Control for Multi-Agent Reinforcement Learning in Video Game AI.","publication_year":2019,"publication_date":"2019-05-24","ids":{"openalex":"https://openalex.org/W2946025546","mag":"2946025546"},"language":"en","primary_location":{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-114158","doi":null,"is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-114158","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference paper"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":[],"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/A5101540919","display_name":"Lei Han","orcid":"https://orcid.org/0000-0003-1404-2415","observed_orcids":["https://orcid.org/0000-0003-1404-2415"]},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Han","raw_affiliation_strings":["Tencent (China), Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-1404-2415","affiliations":[{"raw_affiliation_string":"Tencent (China), Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101404135","display_name":"Peng Sun","orcid":"https://orcid.org/0000-0002-8187-9736","observed_orcids":["https://orcid.org/0000-0002-8187-9736"]},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Sun","raw_affiliation_strings":["Tencent (China), Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-8187-9736","affiliations":[{"raw_affiliation_string":"Tencent (China), Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002080576","display_name":"Yali Du","orcid":"https://orcid.org/0000-0001-5683-2621","observed_orcids":["https://orcid.org/0000-0001-5683-2621"]},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Yali Du","raw_affiliation_strings":["University of Technology Sydney, Sydney, Australia"],"raw_orcid":"https://orcid.org/0000-0001-5683-2621","affiliations":[{"raw_affiliation_string":"University of Technology Sydney, Sydney, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101525654","display_name":"Jiechao Xiong","orcid":"https://orcid.org/0000-0002-1154-9053","observed_orcids":["https://orcid.org/0000-0002-1154-9053"]},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiechao Xiong","raw_affiliation_strings":["Tencent (China), Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-1154-9053","affiliations":[{"raw_affiliation_string":"Tencent (China), Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103567145","display_name":"Qing Wang","orcid":"https://orcid.org/0009-0004-8834-957X","observed_orcids":["https://orcid.org/0009-0004-8834-957X"]},"institutions":[{"id":"https://openalex.org/I204465549","display_name":"Washington University in St. Louis","ror":"https://ror.org/01yc7t268","country_code":"US","type":"education","lineage":["https://openalex.org/I204465549"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qing Wang","raw_affiliation_strings":["Washington University in St. Louis, St Louis, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Washington University in St. Louis, St Louis, United States","institution_ids":["https://openalex.org/I204465549"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072867363","display_name":"Xinghai Sun","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinghai Sun","raw_affiliation_strings":["Tencent (China), Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent (China), Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110503384","display_name":"Han Liu","orcid":"https://orcid.org/0000-0002-4627-0431","observed_orcids":["https://orcid.org/0000-0002-4627-0431"]},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Han Liu","raw_affiliation_strings":["Princeton University, Princeton, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Princeton University, Princeton, United States","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100378792","display_name":"Tong Zhang","orcid":"https://orcid.org/0000-0002-5511-2558","observed_orcids":["https://orcid.org/0000-0002-5511-2558","https://orcid.org/0000-0001-5818-4285","https://orcid.org/0000-0002-7025-6365","https://orcid.org/0000-0002-8838-4963","https://orcid.org/0000-0001-6212-4891","https://orcid.org/0000-0002-3506-0180","https://orcid.org/0000-0002-6807-0641","https://orcid.org/0000-0003-1148-4322","https://orcid.org/0000-0002-0131-0129","https://orcid.org/0000-0001-8163-3050","https://orcid.org/0000-0002-3481-6062"]},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tong Zhang","raw_affiliation_strings":["Tencent (China), Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-7025-6365","affiliations":[{"raw_affiliation_string":"Tencent (China), Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.142,"has_fulltext":false,"cited_by_count":37,"citation_normalized_percentile":{"value":0.83797036,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2576","last_page":"2585"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9951000213623047,"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":0.9951000213623047,"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":0.004600000102072954,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.0,"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/multi-agent-reinforcement-learning","display_name":"multi-agent reinforcement learning","score":0.9980000257492065},{"id":"https://openalex.org/keywords/video-game-ai","display_name":"video game AI","score":0.968999981880188},{"id":"https://openalex.org/keywords/agent-communication","display_name":"agent communication","score":0.9020000100135803},{"id":"https://openalex.org/keywords/starcraft-ii","display_name":"StarCraft II","score":0.8029999732971191},{"id":"https://openalex.org/keywords/parallel-exploration","display_name":"parallel exploration","score":0.5509999990463257}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8177990913391113},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7533486485481262},{"id":"https://openalex.org/C3018412434","wikidata":"https://www.wikidata.org/wiki/Q7889","display_name":"Video game","level":2,"score":0.672289252281189},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.5688890218734741},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5158993005752563},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4624035954475403},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.4333420395851135},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3307563364505768},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.18719422817230225},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06590196490287781},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-114158","doi":null,"is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-114158","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference paper"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-103623","doi":null,"is_oa":false,"landing_page_url":"http://lbdiscover.ust.hk/uresolver?url_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rfr_id=info:sid/HKUST:SPI&rft.genre=article&rft.issn=&rft.volume=2019&rft.issue=&rft.date=2019&rft.spage=4558&rft.aulast=Han&rft.aufirst=&rft.atitle=Grid-wise+control+for+multi-agent+reinforcement+learning+in+video+game+AI&rft.title=36th+International+Conference+on+Machine+Learning%2C+ICML+2019","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference paper"},{"id":"pmh:oai:repository.ust.hk:1783.1-103623","doi":null,"is_oa":false,"landing_page_url":"http://repository.ust.hk/ir/Record/1783.1-103623","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference paper"},{"id":"pmh:oai:repository.ust.hk:1783.1-114158","doi":null,"is_oa":false,"landing_page_url":"http://repository.ust.hk/ir/Record/1783.1-114158","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference paper"},{"id":"mag:2946025546","doi":null,"is_oa":false,"landing_page_url":"http://proceedings.mlr.press/v97/han19a/han19a.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306419644","display_name":"International Conference on Machine Learning","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"International Conference on Machine Learning","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W33871791","https://openalex.org/W1641379095","https://openalex.org/W1745334888","https://openalex.org/W1771410628","https://openalex.org/W1903029394","https://openalex.org/W1977655452","https://openalex.org/W2074500080","https://openalex.org/W2099618002","https://openalex.org/W2100495367","https://openalex.org/W2119717200","https://openalex.org/W2121863487","https://openalex.org/W2145339207","https://openalex.org/W2165150801","https://openalex.org/W2169393322","https://openalex.org/W2173248099","https://openalex.org/W2257979135","https://openalex.org/W2395575420","https://openalex.org/W2412782625","https://openalex.org/W2526379199","https://openalex.org/W2546571074","https://openalex.org/W2604283518","https://openalex.org/W2749807327","https://openalex.org/W2766447205","https://openalex.org/W2786036274","https://openalex.org/W2885514323","https://openalex.org/W2963163009","https://openalex.org/W2963407617","https://openalex.org/W2964338167","https://openalex.org/W3011120880","https://openalex.org/W3093287223"],"related_works":["https://openalex.org/W4385488920","https://openalex.org/W4390187200","https://openalex.org/W4283170178","https://openalex.org/W4206324902","https://openalex.org/W2750605955","https://openalex.org/W2913326990","https://openalex.org/W4312883490","https://openalex.org/W4320561151","https://openalex.org/W4417081754","https://openalex.org/W4313291205"],"abstract_inverted_index":{"We":[0,175],"consider":[1],"the":[2,14,24,55,63,78,92,95,101,115,126,132,137,147,177,180,194],"problem":[3],"of":[4,26,43,76,125,179],"multi-agent":[5,186],"reinforcement":[6,168],"learning":[7,169],"(MARL)":[8],"in":[9,18,183,188],"video":[10],"game":[11],"AI,":[12],"where":[13],"agents":[15,27,44,79],"are":[16],"located":[17],"a":[19,67,72,105,111],"spatial":[20,73],"grid-world":[21],"environment":[22],"and":[23,31,80,173],"number":[25,42],"varies":[28],"both":[29],"within":[30],"across":[32],"episodes.":[33],"The":[34,159],"challenge":[35],"is":[36],"to":[37,157],"flexibly":[38],"control":[39],"an":[40],"arbitrary":[41],"while":[45],"achieving":[46],"effective":[47],"collaboration.":[48],"Existing":[49],"MARL":[50],"methods":[51],"usually":[52],"suffer":[53],"from":[54,94],"trade-off":[56],"between":[57],"these":[58],"two":[59],"considerations.":[60],"To":[61],"address":[62],"issue,":[64],"we":[65,109],"propose":[66],"novel":[68],"architecture":[69,119],"that":[70,146],"learns":[71],"joint":[74],"representation":[75],"all":[77],"outputs":[81],"grid-wise":[82],"actions.":[83],"Each":[84],"agent":[85,122,152],"will":[86],"be":[87,154,163],"controlled":[88],"independently":[89],"by":[90,131,150,193],"taking":[91],"action":[93],"grid":[96,106],"it":[97],"occupies.":[98],"By":[99],"viewing":[100],"state":[102],"information":[103],"as":[104,114],"feature":[107],"map,":[108],"employ":[110],"convolutional":[112,134,140],"encoder-decoder":[113],"policy":[116],"network.":[117],"This":[118],"naturally":[120],"promotes":[121],"communication":[123],"because":[124],"large":[127],"receptive":[128],"field":[129],"provided":[130],"stacked":[133],"layers.":[135],"Moreover,":[136],"spatially":[138],"shared":[139],"parameters":[141],"enable":[142],"fast":[143],"parallel":[144],"exploration":[145],"experiences":[148],"discovered":[149],"one":[151],"can":[153,162],"immediately":[155],"transferred":[156],"others.":[158],"proposed":[160,181],"method":[161,182],"conveniently":[164],"integrated":[165],"with":[166],"general":[167],"algorithms,":[170],"e.g.,":[171],"PPO":[172],"Q-leaming.":[174],"demonstrate":[176],"effectiveness":[178],"extensive":[184],"challenging":[185],"tasks":[187],"StarCraft":[189],"II.":[190],"Copyright":[191],"2019":[192],"author(s).":[195]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3}],"updated_date":"2026-11-11T12:16:26.678958","created_date":"2019-05-29T00:00:00"}