{"id":"https://openalex.org/W4391054859","doi":"https://doi.org/10.1145/3631085.3631337","title":"Scale-Invariant Reinforcement Learning in Real-Time Strategy Games","display_name":"Scale-Invariant Reinforcement Learning in Real-Time Strategy Games","publication_year":2023,"publication_date":"2023-11-06","ids":{"openalex":"https://openalex.org/W4391054859","doi":"https://doi.org/10.1145/3631085.3631337"},"language":"en","primary_location":{"id":"doi:10.1145/3631085.3631337","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3631085.3631337","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd Brazilian Symposium on Games and Digital Entertainment","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/A5076246111","display_name":"Marcelo Luiz Harry Diniz Lemos","orcid":"https://orcid.org/0009-0001-5475-5236"},"institutions":[{"id":"https://openalex.org/I110200422","display_name":"Universidade Federal de Minas Gerais","ror":"https://ror.org/0176yjw32","country_code":"BR","type":"education","lineage":["https://openalex.org/I110200422"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Marcelo Luiz Harry Diniz Lemos","raw_affiliation_strings":[", Universidade Federal de Minas Gerais, Brazil"],"raw_orcid":"https://orcid.org/0009-0001-5475-5236","affiliations":[{"raw_affiliation_string":", Universidade Federal de Minas Gerais, Brazil","institution_ids":["https://openalex.org/I110200422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007916872","display_name":"Ronaldo e Silva Vieira","orcid":"https://orcid.org/0000-0002-7109-0897"},"institutions":[{"id":"https://openalex.org/I110200422","display_name":"Universidade Federal de Minas Gerais","ror":"https://ror.org/0176yjw32","country_code":"BR","type":"education","lineage":["https://openalex.org/I110200422"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Ronaldo E Silva Vieira","raw_affiliation_strings":[", Universidade Federal de Minas Gerais, Brazil"],"raw_orcid":"https://orcid.org/0000-0002-7109-0897","affiliations":[{"raw_affiliation_string":", Universidade Federal de Minas Gerais, Brazil","institution_ids":["https://openalex.org/I110200422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048925954","display_name":"Anderson Rocha Tavares","orcid":"https://orcid.org/0000-0002-8530-6468"},"institutions":[{"id":"https://openalex.org/I130442723","display_name":"Universidade Federal do Rio Grande do Sul","ror":"https://ror.org/041yk2d64","country_code":"BR","type":"education","lineage":["https://openalex.org/I130442723"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Anderson Rocha Tavares","raw_affiliation_strings":[", Universidade Federal do Rio Grande do Sul, Brazil"],"raw_orcid":"https://orcid.org/0000-0002-8530-6468","affiliations":[{"raw_affiliation_string":", Universidade Federal do Rio Grande do Sul, Brazil","institution_ids":["https://openalex.org/I130442723"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026278797","display_name":"Leandro Soriano Marcolino","orcid":"https://orcid.org/0000-0002-3337-8611"},"institutions":[{"id":"https://openalex.org/I67415387","display_name":"Lancaster University","ror":"https://ror.org/04f2nsd36","country_code":"GB","type":"education","lineage":["https://openalex.org/I67415387"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Leandro Soriano Marcolino","raw_affiliation_strings":[", Lancaster University, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0002-3337-8611","affiliations":[{"raw_affiliation_string":", Lancaster University, United Kingdom","institution_ids":["https://openalex.org/I67415387"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073879771","display_name":"Luiz Chaimowicz","orcid":"https://orcid.org/0000-0001-8156-9941"},"institutions":[{"id":"https://openalex.org/I110200422","display_name":"Universidade Federal de Minas Gerais","ror":"https://ror.org/0176yjw32","country_code":"BR","type":"education","lineage":["https://openalex.org/I110200422"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Luiz Chaimowicz","raw_affiliation_strings":[", Universidade Federal de Minas Gerais, Brazil"],"raw_orcid":"https://orcid.org/0000-0001-8156-9941","affiliations":[{"raw_affiliation_string":", Universidade Federal de Minas Gerais, Brazil","institution_ids":["https://openalex.org/I110200422"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"11","last_page":"19"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9952999949455261,"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":0.9952999949455261,"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/T11206","display_name":"Model Reduction and Neural Networks","score":0.9930999875068665,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11574","display_name":"Artificial Intelligence in Games","score":0.9783999919891357,"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":0.8611650466918945},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.779477596282959},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.6873689293861389},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.585981547832489},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.5550671219825745},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4855337142944336},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.472304105758667},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.4692402184009552},{"id":"https://openalex.org/keywords/video-game","display_name":"Video game","score":0.4483713209629059},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4446238875389099},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3822299540042877},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.09281492233276367}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8611650466918945},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.779477596282959},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.6873689293861389},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.585981547832489},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.5550671219825745},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4855337142944336},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.472304105758667},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.4692402184009552},{"id":"https://openalex.org/C3018412434","wikidata":"https://www.wikidata.org/wiki/Q7889","display_name":"Video game","level":2,"score":0.4483713209629059},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4446238875389099},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3822299540042877},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.09281492233276367},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3631085.3631337","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3631085.3631337","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd Brazilian Symposium on Games and Digital Entertainment","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.lancs.ac.uk:204511","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306401916","display_name":"Lancaster EPrints (Lancaster University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67415387","host_organization_name":"Lancaster University","host_organization_lineage":["https://openalex.org/I67415387"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Contribution in Book/Report/Proceedings"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W2102605133","https://openalex.org/W2109255472","https://openalex.org/W2150468603","https://openalex.org/W2257979135","https://openalex.org/W2296073425","https://openalex.org/W2618530766","https://openalex.org/W2887122272","https://openalex.org/W2982316857","https://openalex.org/W3037164854","https://openalex.org/W3103780890","https://openalex.org/W3114511015","https://openalex.org/W3165143166","https://openalex.org/W4205504069","https://openalex.org/W4306680355"],"related_works":["https://openalex.org/W2953234277","https://openalex.org/W2626256601","https://openalex.org/W2900413183","https://openalex.org/W4390975304","https://openalex.org/W147410782","https://openalex.org/W3022252430","https://openalex.org/W3103989898","https://openalex.org/W4287804464","https://openalex.org/W803346624","https://openalex.org/W3021077427"],"abstract_inverted_index":{"Real-time":[0],"strategy":[1],"games":[2,43],"present":[3],"a":[4,124,158],"significant":[5],"challenge":[6],"for":[7,164],"artificial":[8],"game-playing":[9],"agents":[10,24,167],"by":[11,86,102,113],"combining":[12,87],"several":[13,45],"fundamental":[14],"AI":[15],"problems.":[16],"Despite":[17],"the":[18,55,59,98,103,108,133,138,153],"difficulties,":[19],"attempts":[20],"to":[21,118,140],"create":[22],"autonomous":[23,166],"using":[25],"Deep":[26],"Reinforcement":[27],"Learning":[28],"have":[29],"been":[30],"successful,":[31],"with":[32,49,90],"bots":[33],"like":[34],"AlphaStar":[35],"beating":[36],"even":[37],"expert":[38],"human":[39],"players.":[40],"Many":[41],"RTS":[42,170],"include":[44],"distinct":[46],"world":[47],"maps":[48],"different":[50],"dimensions,":[51,136],"which":[52],"may":[53],"affect":[54],"agent\u2019s":[56],"observation":[57,135],"and":[58,76,106,156,161],"representation":[60,126],"of":[61,111,127,132],"game":[62,129,171],"states.":[63],"However,":[64],"most":[65],"current":[66],"architectures":[67],"suffer":[68],"from":[69],"fixed":[70],"input":[71],"sizes":[72],"or":[73],"require":[74],"extensive":[75],"complex":[77],"training.":[78],"In":[79],"this":[80],"paper,":[81],"we":[82,96],"overcome":[83],"these":[84],"limitations":[85],"Grid-Wise":[88],"Control":[89],"Spatial":[91],"Pyramid":[92],"Pooling":[93],"(SPP).":[94],"Specifically,":[95],"employ":[97],"encoder-decoder":[99],"framework":[100],"provided":[101],"GridNet":[104],"architecture":[105],"enhance":[107],"critic":[109],"component":[110],"PPO":[112],"adding":[114],"an":[115],"SPP":[116],"layer":[117,122],"it.":[119],"The":[120],"new":[121],"generates":[123],"standardized":[125],"any":[128,143],"state":[130],"regardless":[131],"initial":[134],"allowing":[137],"agent":[139],"act":[141],"on":[142],"map.":[144],"Our":[145],"evaluation":[146],"demonstrates":[147],"that":[148],"our":[149],"proposed":[150],"method":[151],"improves":[152],"models\u2019":[154],"flexibility":[155],"provides":[157],"more":[159],"effective":[160],"efficient":[162],"solution":[163],"training":[165],"in":[168],"multiple":[169],"scenarios.":[172]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}