{"id":"https://openalex.org/W2090049859","doi":"https://doi.org/10.1109/icarsc.2014.6849775","title":"Learning robotic soccer controllers with the Q-Batch update-rule","display_name":"Learning robotic soccer controllers with the Q-Batch update-rule","publication_year":2014,"publication_date":"2014-05-01","ids":{"openalex":"https://openalex.org/W2090049859","doi":"https://doi.org/10.1109/icarsc.2014.6849775","mag":"2090049859"},"language":"en","primary_location":{"id":"doi:10.1109/icarsc.2014.6849775","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icarsc.2014.6849775","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Autonomous Robot Systems and Competitions (ICARSC)","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/A5015159230","display_name":"Jo\u00e3o Paulo Silva Cunha","orcid":"https://orcid.org/0000-0003-4131-9045"},"institutions":[{"id":"https://openalex.org/I60858718","display_name":"University of Aveiro","ror":"https://ror.org/00nt41z93","country_code":"PT","type":"education","lineage":["https://openalex.org/I60858718"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Joao Cunha","raw_affiliation_strings":["Institute of Electronics and Telematics Engineering of Aveiro, University of Aveiro"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Electronics and Telematics Engineering of Aveiro, University of Aveiro","institution_ids":["https://openalex.org/I60858718"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008862363","display_name":"Rui Serra","orcid":"https://orcid.org/0000-0001-7940-390X"},"institutions":[{"id":"https://openalex.org/I60858718","display_name":"University of Aveiro","ror":"https://ror.org/00nt41z93","country_code":"PT","type":"education","lineage":["https://openalex.org/I60858718"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Rui Serra","raw_affiliation_strings":["Department of Electronics Telecomunications, and Informatics, University of Aveiro"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronics Telecomunications, and Informatics, University of Aveiro","institution_ids":["https://openalex.org/I60858718"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055569781","display_name":"Nuno Lau","orcid":"https://orcid.org/0000-0003-0513-158X"},"institutions":[{"id":"https://openalex.org/I60858718","display_name":"University of Aveiro","ror":"https://ror.org/00nt41z93","country_code":"PT","type":"education","lineage":["https://openalex.org/I60858718"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Nuno Lau","raw_affiliation_strings":["Universidade de Aveiro, Aveiro, Aveiro, PT"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universidade de Aveiro, Aveiro, Aveiro, PT","institution_ids":["https://openalex.org/I60858718"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044604176","display_name":"Lu\u00eds Seabra Lopes","orcid":"https://orcid.org/0000-0002-5719-5019"},"institutions":[{"id":"https://openalex.org/I60858718","display_name":"University of Aveiro","ror":"https://ror.org/00nt41z93","country_code":"PT","type":"education","lineage":["https://openalex.org/I60858718"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Luis Seabra Lopes","raw_affiliation_strings":["Institute of Electronics and Telematics Engineering of Aveiro, University of Aveiro"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Electronics and Telematics Engineering of Aveiro, University of Aveiro","institution_ids":["https://openalex.org/I60858718"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043337599","display_name":"Ant\u00f3nio J. R. Neves","orcid":"https://orcid.org/0000-0001-5433-6667"},"institutions":[{"id":"https://openalex.org/I60858718","display_name":"University of Aveiro","ror":"https://ror.org/00nt41z93","country_code":"PT","type":"education","lineage":["https://openalex.org/I60858718"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Antonio J. R. Neves","raw_affiliation_strings":["Institute of Electronics and Telematics Engineering of Aveiro, University of Aveiro"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Electronics and Telematics Engineering of Aveiro, University of Aveiro","institution_ids":["https://openalex.org/I60858718"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I60858718"],"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":"20","issue":null,"first_page":"134","last_page":"139"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9973000288009644,"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":0.9973000288009644,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9839000105857849,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10821","display_name":"Cardiovascular Function and Risk Factors","score":0.9700000286102295,"subfield":{"id":"https://openalex.org/subfields/2705","display_name":"Cardiology and Cardiovascular Medicine"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7682321071624756},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7575560808181763},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6149961948394775},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5785632729530334},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5778601765632629},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.547374963760376},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.44237229228019714},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.3649212121963501},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34308505058288574},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13631337881088257}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7682321071624756},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7575560808181763},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6149961948394775},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5785632729530334},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5778601765632629},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.547374963760376},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.44237229228019714},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.3649212121963501},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34308505058288574},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13631337881088257},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icarsc.2014.6849775","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icarsc.2014.6849775","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Autonomous Robot Systems and Competitions (ICARSC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W166862392","https://openalex.org/W192920577","https://openalex.org/W1597989182","https://openalex.org/W1825869920","https://openalex.org/W2024893668","https://openalex.org/W2073384958","https://openalex.org/W2101786389","https://openalex.org/W2121863487","https://openalex.org/W2127412976","https://openalex.org/W2143908786","https://openalex.org/W4214717370","https://openalex.org/W4299401133"],"related_works":["https://openalex.org/W2907045084","https://openalex.org/W2618719410","https://openalex.org/W3211352205","https://openalex.org/W4319083788","https://openalex.org/W3022038857","https://openalex.org/W2065963568","https://openalex.org/W2540676782","https://openalex.org/W3041071886","https://openalex.org/W4306666666","https://openalex.org/W2002867377"],"abstract_inverted_index":{"Robotic":[0],"soccer":[1,62],"provides":[2],"a":[3,27,43,53,108,151],"rich":[4],"environment":[5,15,110],"for":[6,30],"the":[7,22,31,38,50,65,68,77,81,93,114,120,141,148],"development":[8,32],"of":[9,21,33,40,52,67,80,85,119,154],"Reinforcement":[10],"Learning":[11],"controllers.":[12,24],"The":[13,73,117],"competitive":[14],"imposes":[16],"strong":[17],"requirements":[18],"on":[19,107,113],"performance":[20,118],"developed":[23,104],"RL":[25,57,87,134],"offers":[26],"valuable":[28],"alternative":[29],"efficient":[34],"controllers":[35,63,122,128],"while":[36,129],"avoiding":[37],"hassle":[39],"parameter":[41],"tuning":[42],"hand":[44],"coded":[45],"policy.":[46,95],"This":[47],"paper":[48],"presents":[49],"application":[51],"recently":[54],"proposed":[55,142],"Batch":[56,86],"update-rule":[58,75],"to":[59,88,126,146],"learn":[60,147],"robotic":[61],"in":[64,150],"context":[66],"RoboCup":[69],"Middle":[70],"Size":[71],"League.":[72],"Q-Batch":[74],"exploits":[76],"episodic":[78],"structure":[79],"data":[82],"collection":[83],"phase":[84],"efficiently":[89],"evaluate":[90],"and":[91,105,111],"improve":[92],"learned":[94,121],"Three":[96],"different":[97],"learning":[98],"tasks,":[99],"with":[100,132],"increasing":[101],"difficulty,":[102],"were":[103,136],"applied":[106],"simulated":[109],"later":[112],"physical":[115],"robot.":[116],"is":[123,144],"mostly":[124],"compared":[125],"hand-tuned":[127],"some":[130],"comparisons":[131],"other":[133],"methods":[135],"performed.":[137],"Results":[138],"show":[139],"that":[140],"approach":[143],"able":[145],"tasks":[149],"reduced":[152],"amount":[153],"time,":[155],"even":[156],"outperforming":[157],"existing":[158],"hand-coded":[159],"solutions.":[160]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
