{"id":"https://openalex.org/W2802184653","doi":"https://doi.org/10.24963/ijcai.2018/377","title":"Algorithms or Actions? A Study in Large-Scale Reinforcement Learning","display_name":"Algorithms or Actions? A Study in Large-Scale Reinforcement Learning","publication_year":2018,"publication_date":"2018-07-01","ids":{"openalex":"https://openalex.org/W2802184653","doi":"https://doi.org/10.24963/ijcai.2018/377","mag":"2802184653"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2018/377","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2018/377","pdf_url":"https://www.ijcai.org/proceedings/2018/0377.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2018/0377.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048925954","display_name":"Anderson Rocha Tavares","orcid":"https://orcid.org/0000-0002-8530-6468"},"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"]},{"id":"https://openalex.org/I4210156583","display_name":"Laboratoire d'Informatique de Paris-Nord","ror":"https://ror.org/05g1zjw44","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I4210091279","https://openalex.org/I4210156583","https://openalex.org/I4210159245"]}],"countries":["BR","FR"],"is_corresponding":false,"raw_author_name":"Anderson Rocha Tavares","raw_affiliation_strings":["Computer Science Department -- Universidade Federal de Minas Gerais"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department -- Universidade Federal de Minas Gerais","institution_ids":["https://openalex.org/I110200422","https://openalex.org/I4210156583"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030705678","display_name":"Sivasubramanian Anbalagan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sivasubramanian Anbalagan","raw_affiliation_strings":["School of Computing and Communications -- Lancaster University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing and Communications -- Lancaster University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026278797","display_name":"Leandro Soriano Marcolino","orcid":"https://orcid.org/0000-0002-3337-8611"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Leandro Soriano Marcolino","raw_affiliation_strings":["School of Computing and Communications -- Lancaster University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing and Communications -- Lancaster University","institution_ids":[]}]},{"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"]},{"id":"https://openalex.org/I4210156583","display_name":"Laboratoire d'Informatique de Paris-Nord","ror":"https://ror.org/05g1zjw44","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I4210091279","https://openalex.org/I4210156583","https://openalex.org/I4210159245"]}],"countries":["BR","FR"],"is_corresponding":false,"raw_author_name":"Luiz Chaimowicz","raw_affiliation_strings":["Computer Science Department -- Universidade Federal de Minas Gerais"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department -- Universidade Federal de Minas Gerais","institution_ids":["https://openalex.org/I110200422","https://openalex.org/I4210156583"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":14,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2717","last_page":"2723"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9937000274658203,"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":0.9937000274658203,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.9193412065505981},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7527579069137573},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6002956628799438},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5605865120887756},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5346072912216187},{"id":"https://openalex.org/keywords/dilemma","display_name":"Dilemma","score":0.5159607529640198},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5022313594818115},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.484181672334671},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4814733564853668},{"id":"https://openalex.org/keywords/function-approximation","display_name":"Function approximation","score":0.45728227496147156},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.446941614151001},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.41642001271247864},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3281935453414917},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.21332886815071106},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16062775254249573},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.11123725771903992}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9193412065505981},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7527579069137573},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6002956628799438},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5605865120887756},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5346072912216187},{"id":"https://openalex.org/C2778496695","wikidata":"https://www.wikidata.org/wiki/Q254128","display_name":"Dilemma","level":2,"score":0.5159607529640198},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5022313594818115},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.484181672334671},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4814733564853668},{"id":"https://openalex.org/C91873725","wikidata":"https://www.wikidata.org/wiki/Q3445816","display_name":"Function approximation","level":3,"score":0.45728227496147156},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.446941614151001},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.41642001271247864},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3281935453414917},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.21332886815071106},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16062775254249573},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.11123725771903992},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.24963/ijcai.2018/377","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2018/377","pdf_url":"https://www.ijcai.org/proceedings/2018/0377.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.lancs.ac.uk:125040","is_oa":true,"landing_page_url":null,"pdf_url":"https://eprints.lancs.ac.uk/id/eprint/125040/4/ijcai_2018.pdf","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Contribution in Book/Report/Proceedings"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2018/377","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2018/377","pdf_url":"https://www.ijcai.org/proceedings/2018/0377.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.6000000238418579,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321091","display_name":"Coordena\u00e7\u00e3o de Aperfei\u00e7oamento de Pessoal de N\u00edvel Superior","ror":"https://ror.org/00x0ma614"},{"id":"https://openalex.org/F4320322025","display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico","ror":"https://ror.org/03swz6y49"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2802184653.pdf","grobid_xml":"https://content.openalex.org/works/W2802184653.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W24656680","https://openalex.org/W1492936035","https://openalex.org/W1495775210","https://openalex.org/W2022504108","https://openalex.org/W2102167689","https://openalex.org/W2109910161","https://openalex.org/W2121517924","https://openalex.org/W2147148915","https://openalex.org/W2156078757","https://openalex.org/W2190692153","https://openalex.org/W2230033167","https://openalex.org/W2602425879","https://openalex.org/W2725258047","https://openalex.org/W2727836376","https://openalex.org/W2729668291","https://openalex.org/W2741302028","https://openalex.org/W2755694566","https://openalex.org/W2794254934","https://openalex.org/W2964056654","https://openalex.org/W3139377883","https://openalex.org/W4214717370","https://openalex.org/W4299335686"],"related_works":["https://openalex.org/W2742483371","https://openalex.org/W3096874164","https://openalex.org/W2166117066","https://openalex.org/W3087814763","https://openalex.org/W2357975469","https://openalex.org/W2136202932","https://openalex.org/W4376605461","https://openalex.org/W4400868993","https://openalex.org/W2361647908","https://openalex.org/W2952356279"],"abstract_inverted_index":{"Large":[0],"state":[1],"and":[2],"action":[3,26],"spaces":[4],"are":[5],"very":[6],"challenging":[7],"to":[8,41,46,62,77],"reinforcement":[9],"learning.":[10],"However,":[11],"in":[12,96],"many":[13],"domains":[14],"there":[15],"is":[16],"a":[17,28,36,67,85],"set":[18],"of":[19,52,70,92],"algorithms":[20,61,95],"available,":[21],"which":[22],"estimate":[23],"the":[24,90],"best":[25],"given":[27],"state.":[29],"Hence,":[30],"agents":[31],"can":[32],"either":[33],"directly":[34],"learn":[35],"performance-maximizing":[37],"mapping":[38],"from":[39,44],"states":[40,45],"actions,":[42],"or":[43],"algorithms.":[47],"We":[48,73],"investigate":[49],"several":[50],"aspects":[51],"this":[53],"dilemma,":[54],"showing":[55],"sufficient":[56],"conditions":[57],"for":[58,66],"learning":[59,93],"over":[60,64,94],"outperform":[63],"actions":[65],"finite":[68],"number":[69],"training":[71],"iterations.":[72],"present":[74],"synthetic":[75],"experiments":[76],"further":[78],"study":[79],"such":[80],"systems.":[81],"Finally,":[82],"we":[83],"propose":[84],"function":[86],"approximation":[87],"approach,":[88],"demonstrating":[89],"effectiveness":[91],"real-time":[97],"strategy":[98],"games.":[99]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}