{"id":"https://openalex.org/W3000763545","doi":"https://doi.org/10.7544/issn1000-1239.2018.20180148","title":"A Deep Q-Network Method Based on Upper Confidence Bound Experience Sampling","display_name":"A Deep Q-Network Method Based on Upper Confidence Bound Experience Sampling","publication_year":2018,"publication_date":"2018-08-01","ids":{"openalex":"https://openalex.org/W3000763545","doi":"https://doi.org/10.7544/issn1000-1239.2018.20180148","mag":"3000763545"},"language":"en","primary_location":{"id":"mag:3000763545","doi":"https://doi.org/10.7544/issn1000-1239.2018.20180148","is_oa":false,"landing_page_url":"http://crad.ict.ac.cn/EN/Y2018/V55/I8/1694","pdf_url":null,"source":{"id":"https://openalex.org/S4210240373","display_name":"Journal of Computer Research and Development","issn_l":"1000-1239","issn":["1000-1239"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["poland-40","russia-white-list-2"],"host_organization":"https://openalex.org/P4310319982","host_organization_name":"Science Press","host_organization_lineage":["https://openalex.org/P4310319982"],"host_organization_lineage_names":["Science Press"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Journal of Computer Research and Development","raw_type":null},"parent_works":[],"lineage":["https://openalex.org/W3000763545"],"child_works_count":0,"type":"article","is_traditional":true,"indexed_in":[],"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/A5074124642","display_name":"Fei Zhu","orcid":"https://orcid.org/0000-0002-2226-2859","observed_orcids":["https://orcid.org/0000-0002-2226-2859"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fei Zhu","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-2226-2859","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007459680","display_name":"Wu Wen","orcid":"https://orcid.org/0000-0003-4074-7670","observed_orcids":["https://orcid.org/0000-0003-4074-7670"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu Wen","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-4074-7670","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100414577","display_name":"Quan Liu","orcid":"https://orcid.org/0000-0002-9036-0290","observed_orcids":["https://orcid.org/0000-0002-9036-0290","https://orcid.org/0009-0001-1406-6145"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Quan Liu","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-9036-0290","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5026708634","display_name":"Yuchen Fu","orcid":"https://orcid.org/0000-0002-7743-3635","observed_orcids":["https://orcid.org/0000-0002-7743-3635"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuchen Fu","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-7743-3635","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6043,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.72318739,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":97},"biblio":{"volume":"55","issue":"8","first_page":"1694","last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.8080999851226807,"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":0.8080999851226807,"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":0.18119999766349792,"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":0.0026000000070780516,"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/deep-q-network","display_name":"deep Q-network","score":0.8619999885559082},{"id":"https://openalex.org/keywords/upper-confidence-bound","display_name":"upper confidence bound","score":0.8849999904632568},{"id":"https://openalex.org/keywords/ecological-momentary-assessment","display_name":"ecological momentary assessment","score":0.902999997138977},{"id":"https://openalex.org/keywords/deep-reinforcement-learning","display_name":"deep reinforcement learning","score":0.7139999866485596},{"id":"https://openalex.org/keywords/exploration-strategy","display_name":"exploration strategy","score":0.5180000066757202}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8577542304992676},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5384414792060852},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.4749353528022766},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.357163667678833},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.15760904550552368},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09654292464256287},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:3000763545","doi":"https://doi.org/10.7544/issn1000-1239.2018.20180148","is_oa":false,"landing_page_url":"http://crad.ict.ac.cn/EN/Y2018/V55/I8/1694","pdf_url":null,"source":{"id":"https://openalex.org/S4210240373","display_name":"Journal of Computer Research and Development","issn_l":"1000-1239","issn":["1000-1239"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["poland-40","russia-white-list-2"],"host_organization":"https://openalex.org/P4310319982","host_organization_name":"Science Press","host_organization_lineage":["https://openalex.org/P4310319982"],"host_organization_lineage_names":["Science Press"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Journal of Computer Research and Development","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3006082176","https://openalex.org/W6959715329","https://openalex.org/W3127446927","https://openalex.org/W3014062588","https://openalex.org/W2801088484","https://openalex.org/W3185121012","https://openalex.org/W3007256995","https://openalex.org/W6893123128","https://openalex.org/W2552220135","https://openalex.org/W3148685027"],"abstract_inverted_index":null,"counts_by_year":[{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":1}],"updated_date":"2026-11-12T12:28:57.059296","created_date":"2020-01-30T00:00:00"}