{"id":"https://openalex.org/W4389332290","doi":"https://doi.org/10.1109/lars/sbr/wre59448.2023.10332923","title":"Deep Reinforcement Learning Applied to IEEE\u2019s Very Small Size Soccer in Cooperative Attack Strategy","display_name":"Deep Reinforcement Learning Applied to IEEE\u2019s Very Small Size Soccer in Cooperative Attack Strategy","publication_year":2023,"publication_date":"2023-10-09","ids":{"openalex":"https://openalex.org/W4389332290","doi":"https://doi.org/10.1109/lars/sbr/wre59448.2023.10332923"},"language":"en","primary_location":{"id":"doi:10.1109/lars/sbr/wre59448.2023.10332923","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lars/sbr/wre59448.2023.10332923","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 Latin American Robotics Symposium (LARS), 2023 Brazilian Symposium on Robotics (SBR), and 2023 Workshop on Robotics in Education (WRE)","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/A5024937646","display_name":"Thiago Filipe de Medeiros","orcid":null},"institutions":[{"id":"https://openalex.org/I107428990","display_name":"Instituto Tecnol\u00f3gico de Aeron\u00e1utica","ror":"https://ror.org/05vh67662","country_code":"BR","type":"education","lineage":["https://openalex.org/I107428990"]},{"id":"https://openalex.org/I4210123805","display_name":"Instituto de Aeron\u00e1utica e Espa\u00e7o","ror":"https://ror.org/025n1fp68","country_code":"BR","type":"other","lineage":["https://openalex.org/I4210123805"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Thiago Filipe de Medeiros","raw_affiliation_strings":["Aeronautics Institute of Technology,Autonomous Computational Systems Lab,São José dos Campos,SP,Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aeronautics Institute of Technology,Autonomous Computational Systems Lab,São José dos Campos,SP,Brazil","institution_ids":["https://openalex.org/I107428990","https://openalex.org/I4210123805"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007059703","display_name":"Takashi Yoneyama","orcid":"https://orcid.org/0000-0001-5375-1076"},"institutions":[{"id":"https://openalex.org/I107428990","display_name":"Instituto Tecnol\u00f3gico de Aeron\u00e1utica","ror":"https://ror.org/05vh67662","country_code":"BR","type":"education","lineage":["https://openalex.org/I107428990"]},{"id":"https://openalex.org/I4210123805","display_name":"Instituto de Aeron\u00e1utica e Espa\u00e7o","ror":"https://ror.org/025n1fp68","country_code":"BR","type":"other","lineage":["https://openalex.org/I4210123805"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Takashi Yoneyama","raw_affiliation_strings":["Aeronautics Institute of Technology,Electronic Engineering Division,São José dos Campos,SP,Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aeronautics Institute of Technology,Electronic Engineering Division,São José dos Campos,SP,Brazil","institution_ids":["https://openalex.org/I107428990","https://openalex.org/I4210123805"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019218502","display_name":"Marcos R. O. A. M\u00e1ximo","orcid":"https://orcid.org/0000-0003-2944-4476"},"institutions":[{"id":"https://openalex.org/I107428990","display_name":"Instituto Tecnol\u00f3gico de Aeron\u00e1utica","ror":"https://ror.org/05vh67662","country_code":"BR","type":"education","lineage":["https://openalex.org/I107428990"]},{"id":"https://openalex.org/I4210123805","display_name":"Instituto de Aeron\u00e1utica e Espa\u00e7o","ror":"https://ror.org/025n1fp68","country_code":"BR","type":"other","lineage":["https://openalex.org/I4210123805"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Marcos R. O. A. M\u00e1ximo","raw_affiliation_strings":["Aeronautics Institute of Technology,Autonomous Computational Systems Lab,São José dos Campos,SP,Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aeronautics Institute of Technology,Autonomous Computational Systems Lab,São José dos Campos,SP,Brazil","institution_ids":["https://openalex.org/I107428990","https://openalex.org/I4210123805"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"349","last_page":"354"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9980999827384949,"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":0.9980999827384949,"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":0.9645000100135803,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9635999798774719,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7354032397270203},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6558824777603149},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4245825409889221},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36224690079689026},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.14035937190055847},{"id":"https://openalex.org/keywords/composite-material","display_name":"Composite material","score":0.09751597046852112}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7354032397270203},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6558824777603149},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4245825409889221},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36224690079689026},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.14035937190055847},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.09751597046852112}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lars/sbr/wre59448.2023.10332923","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lars/sbr/wre59448.2023.10332923","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 Latin American Robotics Symposium (LARS), 2023 Brazilian Symposium on Robotics (SBR), and 2023 Workshop on Robotics in Education (WRE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320314062","display_name":"National Research Council","ror":"https://ror.org/02eq2w707"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1992955514","https://openalex.org/W2041367235","https://openalex.org/W2152240585","https://openalex.org/W2736601468","https://openalex.org/W2964578808","https://openalex.org/W3009915523","https://openalex.org/W3013562692","https://openalex.org/W3120364637","https://openalex.org/W3123244128","https://openalex.org/W4224941573","https://openalex.org/W4298857966","https://openalex.org/W6637967152","https://openalex.org/W6741002519","https://openalex.org/W6769332699"],"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":{"In":[0],"this":[1,161,179],"work,":[2],"we":[3],"use":[4],"a":[5,41,44,52,74,132],"virtual":[6],"learning":[7],"framework":[8],"for":[9],"the":[10,28,33,55,61,68,79,88,92,114,127,134,138,164,174,181,190],"IEEE\u2019s":[11,194],"Very":[12],"Small":[13],"Size":[14],"Soccer":[15],"(VSSS)":[16],"competition":[17],"based":[18],"on":[19,40],"Deep":[20],"Reinforcement":[21],"Learning":[22],"(DRL)":[23],"to":[24,50,71,184],"train":[25],"and":[26,98,120,153,189],"improve":[27],"behavior":[29,140],"of":[30,46,63,76,160,166,176],"agents":[31,101,141],"within":[32],"game":[34],"strategy.":[35],"The":[36,158],"agent":[37,69,116,128],"was":[38,65,85,96,117],"trained":[39,93,118],"scenario":[42],"where":[43,67],"pair":[45],"robots":[47],"must":[48],"cooperate":[49,72],"score":[51],"goal":[53,111],"in":[54,106,142,169,186,193],"adversary":[56],"field.":[57],"To":[58,173],"achieve":[59],"that,":[60],"concept":[62],"Self-Play":[64,168,188],"used,":[66],"learns":[70],"with":[73,100],"copy":[75],"itself.":[77],"Furthermore,":[78],"Proximal":[80],"Policy":[81],"optimization":[82],"(PPO)":[83],"technique":[84,192],"used":[86],"during":[87,129],"training":[89],"process.":[90],"Finally,":[91],"agent\u2019s":[94,136],"performance":[95],"evaluated":[97],"compared":[99],"following":[102],"handmade":[103],"heuristic":[104,139],"behaviors":[105],"two":[107],"scenarios:":[108],"(1)":[109,149],"empty":[110],"(in":[112],"which":[113],"DRL":[115,135],"on)":[119],"(2)":[121,154],"against":[122,151,156],"goalie":[123],"(not":[124],"seen":[125],"by":[126],"train).":[130],"As":[131],"result,":[133],"outperformed":[137],"both":[143],"scenarios":[144],"when":[145],"comparing":[146],"success":[147],"rate:":[148],"99.18%":[150],"81.50%":[152],"32.94%":[155],"28.60%.":[157],"contribution":[159],"work":[162,183],"is":[163,180],"usage":[165],"cooperative":[167],"an":[170],"offensive":[171],"move.":[172],"best":[175],"our":[177],"knowledge,":[178],"first":[182],"succeed":[185],"combining":[187],"PPO":[191],"VSSS.":[195]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}