{"id":"https://openalex.org/W2780635050","doi":"https://doi.org/10.1007/978-3-319-70836-2_11","title":"Mixed-Policy Asynchronous Deep Q-Learning","display_name":"Mixed-Policy Asynchronous Deep Q-Learning","publication_year":2017,"publication_date":"2017-12-20","ids":{"openalex":"https://openalex.org/W2780635050","doi":"https://doi.org/10.1007/978-3-319-70836-2_11","mag":"2780635050"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-319-70836-2_11","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-319-70836-2_11","pdf_url":null,"source":{"id":"https://openalex.org/S2764905038","display_name":"Advances in intelligent systems and computing","issn_l":"2194-5357","issn":["2194-5357","2194-5365"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Intelligent Systems and Computing","raw_type":"book-chapter"},"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/A5081040128","display_name":"David Sim\u00f5es","orcid":"https://orcid.org/0000-0002-6464-8012"},"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":true,"raw_author_name":"David Sim\u00f5es","raw_affiliation_strings":["DETI/UA - Electronics, Telecommunications and Informatics Department, University of Aveiro, Aveiro, Portugal","IEETA - Institute of Electronics and Informatics Engineering of Aveiro, University of Aveiro, Aveiro, Portugal","LIACC - Artificial Intelligence and Computer Science Lab, Porto, Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DETI/UA - Electronics, Telecommunications and Informatics Department, University of Aveiro, Aveiro, Portugal","institution_ids":["https://openalex.org/I60858718"]},{"raw_affiliation_string":"IEETA - Institute of Electronics and Informatics Engineering of Aveiro, University of Aveiro, Aveiro, Portugal","institution_ids":["https://openalex.org/I60858718"]},{"raw_affiliation_string":"LIACC - Artificial Intelligence and Computer Science Lab, Porto, Portugal","institution_ids":[]}]},{"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":["DETI/UA - Electronics, Telecommunications and Informatics Department, University of Aveiro, Aveiro, Portugal","IEETA - Institute of Electronics and Informatics Engineering of Aveiro, University of Aveiro, Aveiro, Portugal","Institute of Electronics and Telematics Engineering of Aveiro (IEETA), Universidade de Aveiro, Aveiro, Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DETI/UA - Electronics, Telecommunications and Informatics Department, University of Aveiro, Aveiro, Portugal","institution_ids":["https://openalex.org/I60858718"]},{"raw_affiliation_string":"IEETA - Institute of Electronics and Informatics Engineering of Aveiro, University of Aveiro, Aveiro, Portugal","institution_ids":["https://openalex.org/I60858718"]},{"raw_affiliation_string":"Institute of Electronics and Telematics Engineering of Aveiro (IEETA), Universidade de Aveiro, Aveiro, Portugal","institution_ids":["https://openalex.org/I60858718"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089812166","display_name":"Lu\u00eds Paulo Reis","orcid":"https://orcid.org/0000-0002-4709-1718"},"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"]},{"id":"https://openalex.org/I99682543","display_name":"University of Minho","ror":"https://ror.org/037wpkx04","country_code":"PT","type":"education","lineage":["https://openalex.org/I99682543"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Lu\u00eds Paulo Reis","raw_affiliation_strings":["DSI/EEUM - Information Systems Department, School of Engineering, University of Minho, Guimar\u00e3es, Portugal","IEETA - Institute of Electronics and Informatics Engineering of Aveiro, University of Aveiro, Aveiro, Portugal","LIACC - Artificial Intelligence and Computer Science Lab, Porto, Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DSI/EEUM - Information Systems Department, School of Engineering, University of Minho, Guimar\u00e3es, Portugal","institution_ids":["https://openalex.org/I99682543"]},{"raw_affiliation_string":"IEETA - Institute of Electronics and Informatics Engineering of Aveiro, University of Aveiro, Aveiro, Portugal","institution_ids":["https://openalex.org/I60858718"]},{"raw_affiliation_string":"LIACC - Artificial Intelligence and Computer Science Lab, Porto, Portugal","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5081040128"],"corresponding_institution_ids":["https://openalex.org/I60858718"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"129","last_page":"140"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9965000152587891,"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"}},{"id":"https://openalex.org/T11574","display_name":"Artificial Intelligence in Games","score":0.9904999732971191,"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":0.8225520849227905},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7411997318267822},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.6809279322624207},{"id":"https://openalex.org/keywords/nash-equilibrium","display_name":"Nash equilibrium","score":0.6360785365104675},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6137331128120422},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5563143491744995},{"id":"https://openalex.org/keywords/extension","display_name":"Extension (predicate logic)","score":0.5333946347236633},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4827636778354645},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.46451252698898315},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4518449306488037},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.44279319047927856},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.18514662981033325},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.13668668270111084},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09771358966827393},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.07240918278694153}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8225520849227905},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7411997318267822},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.6809279322624207},{"id":"https://openalex.org/C46814582","wikidata":"https://www.wikidata.org/wiki/Q23389","display_name":"Nash equilibrium","level":2,"score":0.6360785365104675},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6137331128120422},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5563143491744995},{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.5333946347236633},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4827636778354645},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.46451252698898315},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4518449306488037},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.44279319047927856},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.18514662981033325},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.13668668270111084},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09771358966827393},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.07240918278694153},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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":1,"locations":[{"id":"doi:10.1007/978-3-319-70836-2_11","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-319-70836-2_11","pdf_url":null,"source":{"id":"https://openalex.org/S2764905038","display_name":"Advances in intelligent systems and computing","issn_l":"2194-5357","issn":["2194-5357","2194-5365"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Intelligent Systems and Computing","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W361876","https://openalex.org/W1533861849","https://openalex.org/W1540725368","https://openalex.org/W1562353621","https://openalex.org/W1566652554","https://openalex.org/W2002256627","https://openalex.org/W2103437045","https://openalex.org/W2120327309","https://openalex.org/W2120846115","https://openalex.org/W2138362680","https://openalex.org/W2145339207","https://openalex.org/W2156289698","https://openalex.org/W2176412452","https://openalex.org/W2743150096","https://openalex.org/W2767130224","https://openalex.org/W2964043796","https://openalex.org/W2964121744","https://openalex.org/W3105048218","https://openalex.org/W6732629455"],"related_works":["https://openalex.org/W2120447654","https://openalex.org/W2977179488","https://openalex.org/W2116677773","https://openalex.org/W2144453115","https://openalex.org/W2128223750","https://openalex.org/W4238532390","https://openalex.org/W4294338060","https://openalex.org/W1491017262","https://openalex.org/W1494824878","https://openalex.org/W4297819361"],"abstract_inverted_index":null,"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
