{"id":"https://openalex.org/W2967070138","doi":"https://doi.org/10.1109/la-cci47412.2019.9036763","title":"Performing Deep Recurrent Double Q-Learning for Atari Games","display_name":"Performing Deep Recurrent Double Q-Learning for Atari Games","publication_year":2019,"publication_date":"2019-11-01","ids":{"openalex":"https://openalex.org/W2967070138","doi":"https://doi.org/10.1109/la-cci47412.2019.9036763","mag":"2967070138"},"language":"en","primary_location":{"id":"doi:10.1109/la-cci47412.2019.9036763","is_oa":false,"landing_page_url":"https://doi.org/10.1109/la-cci47412.2019.9036763","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Latin American Conference on Computational Intelligence (LA-CCI)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1908.06040","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013761088","display_name":"Felipe Moreno-Vera","orcid":"https://orcid.org/0000-0002-2477-9624"},"institutions":[{"id":"https://openalex.org/I4210134504","display_name":"Universidad Cat\u00f3lica San Pablo","ror":"https://ror.org/03db1hz44","country_code":"PE","type":"education","lineage":["https://openalex.org/I4210134504"]}],"countries":["PE"],"is_corresponding":true,"raw_author_name":"Felipe Moreno-Vera","raw_affiliation_strings":["Universidad Cat\u00f3lica San Pablo, Arequipa, Per\u00fa"],"affiliations":[{"raw_affiliation_string":"Universidad Cat\u00f3lica San Pablo, Arequipa, Per\u00fa","institution_ids":["https://openalex.org/I4210134504"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5013761088"],"corresponding_institution_ids":["https://openalex.org/I4210134504"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.08848423,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9965999722480774,"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":0.9898999929428101,"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":0.8637790083885193},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8007131814956665},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.7277094721794128},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7178010940551758},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5736478567123413},{"id":"https://openalex.org/keywords/error-driven-learning","display_name":"Error-driven learning","score":0.47417151927948},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.46868422627449036},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.4243966341018677},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.12704172730445862}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8637790083885193},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8007131814956665},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.7277094721794128},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7178010940551758},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5736478567123413},{"id":"https://openalex.org/C47932503","wikidata":"https://www.wikidata.org/wiki/Q5395689","display_name":"Error-driven learning","level":3,"score":0.47417151927948},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46868422627449036},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.4243966341018677},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.12704172730445862},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/la-cci47412.2019.9036763","is_oa":false,"landing_page_url":"https://doi.org/10.1109/la-cci47412.2019.9036763","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Latin American Conference on Computational Intelligence (LA-CCI)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1908.06040","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1908.06040","pdf_url":"https://arxiv.org/pdf/1908.06040","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"pmh:oai:HAL:hal-02217800v2","is_oa":true,"landing_page_url":"https://hal.science/hal-02217800","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"International Conference on Machine Learning, LatinX in AI Workshop, Jun 2019, Long Beach, United States","raw_type":"Conference papers"},{"id":"doi:10.48550/arxiv.1908.06040","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1908.06040","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1908.06040","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1908.06040","pdf_url":"https://arxiv.org/pdf/1908.06040","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W2064675550","https://openalex.org/W2145339207","https://openalex.org/W2150468603","https://openalex.org/W2155968351","https://openalex.org/W2312609093","https://openalex.org/W2913277521","https://openalex.org/W2962938178","https://openalex.org/W4214717370","https://openalex.org/W6637967152","https://openalex.org/W6677939520"],"related_works":["https://openalex.org/W3213159396","https://openalex.org/W2589804868","https://openalex.org/W2993020264","https://openalex.org/W2973184394","https://openalex.org/W2891764815","https://openalex.org/W2555488107","https://openalex.org/W2962991582","https://openalex.org/W2588283865","https://openalex.org/W2589545309","https://openalex.org/W3111442723","https://openalex.org/W3097894767","https://openalex.org/W2883899184","https://openalex.org/W2922196163","https://openalex.org/W3103078407","https://openalex.org/W2912943342","https://openalex.org/W3122690883","https://openalex.org/W2087767021","https://openalex.org/W3015302423","https://openalex.org/W2963764810","https://openalex.org/W2898827632"],"abstract_inverted_index":{"Currently,":[0],"many":[1],"applications":[2],"in":[3,29,40,75],"Machine":[4],"Learning":[5,23],"are":[6],"based":[7,66],"on":[8,67],"defining":[9],"new":[10],"models":[11],"to":[12,42],"extract":[13],"more":[14],"information":[15,50],"about":[16],"data,":[17],"In":[18,79],"this":[19,80],"case":[20],"Deep":[21,68],"Reinforcement":[22],"with":[24,48],"the":[25,93],"most":[26],"common":[27],"application":[28],"video":[30],"games":[31],"like":[32,101],"Atari,":[33],"Mario,":[34],"and":[35,64,77,98,103],"others":[36],"causes":[37],"an":[38,90],"impact":[39],"how":[41],"computers":[43],"can":[44],"learning":[45],"by":[46,72],"himself":[47],"only":[49],"called":[51],"rewards":[52],"obtained":[53],"from":[54],"any":[55],"action.":[56],"There":[57],"is":[58,89],"a":[59],"lot":[60],"of":[61,92],"algorithms":[62,94,97],"modeled":[63],"implemented":[65],"Recurrent":[69,99],"Q-Learning":[70,96],"proposed":[71,83],"DeepMind":[73],"used":[74],"AlphaZero":[76],"Go.":[78],"document,":[81],"we":[82],"deep":[84],"recurrent":[85],"double":[86],"Q-learning":[87],"that":[88],"improvement":[91],"Double":[95],"Networks":[100],"LSTM":[102],"DRQN.":[104]},"counts_by_year":[],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}