{"id":"https://openalex.org/W2975006769","doi":"https://doi.org/10.1145/3351917.3351989","title":"An Overview of Deep Reinforcement Learning","display_name":"An Overview of Deep Reinforcement Learning","publication_year":2019,"publication_date":"2019-07-19","ids":{"openalex":"https://openalex.org/W2975006769","doi":"https://doi.org/10.1145/3351917.3351989","mag":"2975006769"},"language":"en","primary_location":{"id":"doi:10.1145/3351917.3351989","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3351917.3351989","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 4th International Conference on Automation, Control and Robotics Engineering","raw_type":"proceedings-article"},"type":"article","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/A5003521846","display_name":"LiChun Cao","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"LiChun Cao","raw_affiliation_strings":["College of Computer Science and Techonlogy, Inner Mongolia normal university, Inner Mongolia autonomous region"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Techonlogy, Inner Mongolia normal university, Inner Mongolia autonomous region","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109400208","display_name":"Zhimin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"ZhiMin","raw_affiliation_strings":["College of Computer Science and Techonlogy, Inner Mongolia normal university, Inner Mongolia autonomous region"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Techonlogy, Inner Mongolia normal university, Inner Mongolia autonomous region","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5003521846"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.4556,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.91773739,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.988099992275238,"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":0.988099992275238,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9679999947547913,"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/T12205","display_name":"Time Series Analysis and Forecasting","score":0.944599986076355,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.8784016370773315},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6896857619285583},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.6265527009963989},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6120768785476685},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5008358955383301},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.44150838255882263},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1620274782180786}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8784016370773315},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6896857619285583},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6265527009963989},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6120768785476685},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5008358955383301},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.44150838255882263},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1620274782180786},{"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},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3351917.3351989","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3351917.3351989","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 4th International Conference on Automation, Control and Robotics Engineering","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":39,"referenced_works":["https://openalex.org/W1714211023","https://openalex.org/W1978100507","https://openalex.org/W2056653303","https://openalex.org/W2100495367","https://openalex.org/W2114235770","https://openalex.org/W2118688707","https://openalex.org/W2136922672","https://openalex.org/W2141559645","https://openalex.org/W2145339207","https://openalex.org/W2173248099","https://openalex.org/W2179488730","https://openalex.org/W2257979135","https://openalex.org/W2260756217","https://openalex.org/W2395338531","https://openalex.org/W2557738935","https://openalex.org/W2581082771","https://openalex.org/W2610395436","https://openalex.org/W2732319713","https://openalex.org/W2746553466","https://openalex.org/W2750110103","https://openalex.org/W2761873684","https://openalex.org/W2775725209","https://openalex.org/W2912479652","https://openalex.org/W2950560044","https://openalex.org/W2951799221","https://openalex.org/W2951886768","https://openalex.org/W2963064439","https://openalex.org/W2963068985","https://openalex.org/W2963167649","https://openalex.org/W2963347559","https://openalex.org/W2963362748","https://openalex.org/W2963423916","https://openalex.org/W2963484919","https://openalex.org/W2963590100","https://openalex.org/W2963658727","https://openalex.org/W2963676620","https://openalex.org/W2963864421","https://openalex.org/W2968983352","https://openalex.org/W4249441547"],"related_works":["https://openalex.org/W2731899572","https://openalex.org/W3215138031","https://openalex.org/W3009238340","https://openalex.org/W4321369474","https://openalex.org/W4360585206","https://openalex.org/W4285208911","https://openalex.org/W3082895349","https://openalex.org/W4213079790","https://openalex.org/W2248239756","https://openalex.org/W4323565446"],"abstract_inverted_index":{"As":[0],"a":[1],"new":[2],"machine":[3],"learning":[4,8,43],"method,":[5,73],"deep":[6,41,64,84],"reinforcement":[7,42,85],"has":[9],"made":[10],"important":[11],"progress":[12,51],"in":[13,31,80],"various":[14,81],"fields":[15,82],"of":[16,45,52,63,83],"people's":[17],"production":[18],"and":[19,34,56,77],"life":[20],"since":[21],"it":[22],"was":[23],"proposed.":[24],"However,":[25],"there":[26],"are":[27],"still":[28],"many":[29],"difficulties":[30],"function":[32],"design":[33],"other":[35],"aspects.":[36],"Therefore,":[37],"further":[38],"research":[39,72],"on":[40,59],"is":[44],"great":[46],"significance":[47],"for":[48],"promoting":[49],"the":[50,53,60,69],"whole":[54],"science":[55],"society.":[57],"Based":[58],"basic":[61,70],"theory":[62],"learning,":[65],"this":[66],"paper":[67],"introduces":[68],"theory,":[71],"main":[74],"network":[75],"model":[76],"successful":[78],"application":[79],"learning.":[86]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":1}],"updated_date":"2026-03-04T09:10:02.777135","created_date":"2025-10-10T00:00:00"}