{"id":"https://openalex.org/W3093426589","doi":"https://doi.org/10.1631/fitee.1900533","title":"Deep reinforcement learning: a survey","display_name":"Deep reinforcement learning: a survey","publication_year":2020,"publication_date":"2020-10-15","ids":{"openalex":"https://openalex.org/W3093426589","doi":"https://doi.org/10.1631/fitee.1900533","mag":"3093426589"},"language":"en","primary_location":{"id":"doi:10.1631/fitee.1900533","is_oa":false,"landing_page_url":"https://doi.org/10.1631/fitee.1900533","pdf_url":null,"source":{"id":"https://openalex.org/S4210189857","display_name":"Frontiers of Information Technology & Electronic Engineering","issn_l":"2095-9184","issn":["2095-9184","2095-9230"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers of Information Technology & Electronic Engineering","raw_type":"journal-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":null,"display_name":"Hao-nan Wang","orcid":"https://orcid.org/0000-0002-0792-3858"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hao-nan Wang","raw_affiliation_strings":["Science and Technology on Parallel and Distributed Processing Laboratory, National University of Defense Technology, Changsha, 410000, China"],"raw_orcid":"https://orcid.org/0000-0002-0792-3858","affiliations":[{"raw_affiliation_string":"Science and Technology on Parallel and Distributed Processing Laboratory, National University of Defense Technology, Changsha, 410000, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101683584","display_name":"Ning Liu","orcid":"https://orcid.org/0000-0001-7475-9739"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ning Liu","raw_affiliation_strings":["Science and Technology on Parallel and Distributed Processing Laboratory, National University of Defense Technology, Changsha, 410000, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Science and Technology on Parallel and Distributed Processing Laboratory, National University of Defense Technology, Changsha, 410000, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040322824","display_name":"Yiyun Zhang","orcid":"https://orcid.org/0000-0002-1419-485X"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi-yun Zhang","raw_affiliation_strings":["Science and Technology on Parallel and Distributed Processing Laboratory, National University of Defense Technology, Changsha, 410000, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Science and Technology on Parallel and Distributed Processing Laboratory, National University of Defense Technology, Changsha, 410000, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039795290","display_name":"Dawei Feng","orcid":"https://orcid.org/0000-0002-7587-8905"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Da-wei Feng","raw_affiliation_strings":["Science and Technology on Parallel and Distributed Processing Laboratory, National University of Defense Technology, Changsha, 410000, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Science and Technology on Parallel and Distributed Processing Laboratory, National University of Defense Technology, Changsha, 410000, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051363049","display_name":"Feng Huang","orcid":"https://orcid.org/0000-0002-0740-9373"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Huang","raw_affiliation_strings":["Science and Technology on Parallel and Distributed Processing Laboratory, National University of Defense Technology, Changsha, 410000, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Science and Technology on Parallel and Distributed Processing Laboratory, National University of Defense Technology, Changsha, 410000, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100681030","display_name":"Dongsheng Li","orcid":"https://orcid.org/0000-0001-7725-8040"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dong-sheng Li","raw_affiliation_strings":["Science and Technology on Parallel and Distributed Processing Laboratory, National University of Defense Technology, Changsha, 410000, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Science and Technology on Parallel and Distributed Processing Laboratory, National University of Defense Technology, Changsha, 410000, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100395388","display_name":"Yiming Zhang","orcid":"https://orcid.org/0000-0003-3857-8433"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi-ming Zhang","raw_affiliation_strings":["Science and Technology on Parallel and Distributed Processing Laboratory, National University of Defense Technology, Changsha, 410000, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Science and Technology on Parallel and Distributed Processing Laboratory, National University of Defense Technology, Changsha, 410000, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":{"value":2990,"currency":"USD","value_usd":2990},"apc_paid":null,"fwci":13.1386,"has_fulltext":false,"cited_by_count":279,"citation_normalized_percentile":{"value":0.9901091,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"21","issue":"12","first_page":"1726","last_page":"1744"},"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9897000193595886,"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/T12784","display_name":"Modular Robots and Swarm Intelligence","score":0.9832000136375427,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8006557822227478},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7813801765441895},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6882914900779724},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.5173744559288025},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4922133982181549},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.39875051379203796}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8006557822227478},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7813801765441895},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6882914900779724},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.5173744559288025},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4922133982181549},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39875051379203796}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1631/fitee.1900533","is_oa":false,"landing_page_url":"https://doi.org/10.1631/fitee.1900533","pdf_url":null,"source":{"id":"https://openalex.org/S4210189857","display_name":"Frontiers of Information Technology & Electronic Engineering","issn_l":"2095-9184","issn":["2095-9184","2095-9230"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers of Information Technology & Electronic Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":154,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1575592356","https://openalex.org/W1757796397","https://openalex.org/W1968962398","https://openalex.org/W1988526405","https://openalex.org/W1999874108","https://openalex.org/W2021247827","https://openalex.org/W2061562262","https://openalex.org/W2098774185","https://openalex.org/W2100401322","https://openalex.org/W2100677568","https://openalex.org/W2104733512","https://openalex.org/W2106164082","https://openalex.org/W2108738385","https://openalex.org/W2119717200","https://openalex.org/W2121863487","https://openalex.org/W2124352385","https://openalex.org/W2126909264","https://openalex.org/W2141559645","https://openalex.org/W2145339207","https://openalex.org/W2150468603","https://openalex.org/W2155968351","https://openalex.org/W2163605009","https://openalex.org/W2165150801","https://openalex.org/W2169498096","https://openalex.org/W2173564293","https://openalex.org/W2257979135","https://openalex.org/W2280163991","https://openalex.org/W2290104316","https://openalex.org/W2417786368","https://openalex.org/W2419612459","https://openalex.org/W2434014514","https://openalex.org/W2466175722","https://openalex.org/W2523013761","https://openalex.org/W2528489519","https://openalex.org/W2529477964","https://openalex.org/W2529658650","https://openalex.org/W2546571074","https://openalex.org/W2550182557","https://openalex.org/W2556958149","https://openalex.org/W2561776174","https://openalex.org/W2575705757","https://openalex.org/W2593044849","https://openalex.org/W2596982695","https://openalex.org/W2604373826","https://openalex.org/W2604763608","https://openalex.org/W2614839826","https://openalex.org/W2616964725","https://openalex.org/W2726187156","https://openalex.org/W2727576081","https://openalex.org/W2736601468","https://openalex.org/W2738669288","https://openalex.org/W2739473244","https://openalex.org/W2746553466","https://openalex.org/W2749604329","https://openalex.org/W2749807327","https://openalex.org/W2755546070","https://openalex.org/W2761873684","https://openalex.org/W2765349170","https://openalex.org/W2766610320","https://openalex.org/W2766812927","https://openalex.org/W2767050701","https://openalex.org/W2781726626","https://openalex.org/W2785397462","https://openalex.org/W2786928559","https://openalex.org/W2787501667","https://openalex.org/W2787938642","https://openalex.org/W2788357188","https://openalex.org/W2788904251","https://openalex.org/W2789824229","https://openalex.org/W2795109282","https://openalex.org/W2796290181","https://openalex.org/W2805560727","https://openalex.org/W2805762288","https://openalex.org/W2810754397","https://openalex.org/W2810785043","https://openalex.org/W2824027552","https://openalex.org/W2885550588","https://openalex.org/W2888541716","https://openalex.org/W2889347284","https://openalex.org/W2892620417","https://openalex.org/W2895531857","https://openalex.org/W2903630557","https://openalex.org/W2912757816","https://openalex.org/W2914752403","https://openalex.org/W2923504512","https://openalex.org/W2938321354","https://openalex.org/W2949561945","https://openalex.org/W2949608212","https://openalex.org/W2950359962","https://openalex.org/W2950471160","https://openalex.org/W2950492145","https://openalex.org/W2950794298","https://openalex.org/W2951266961","https://openalex.org/W2951775809","https://openalex.org/W2951948137","https://openalex.org/W2952787800","https://openalex.org/W2954058884","https://openalex.org/W2962715211","https://openalex.org/W2962858248","https://openalex.org/W2962872206","https://openalex.org/W2962938178","https://openalex.org/W2963068985","https://openalex.org/W2963184621","https://openalex.org/W2963190967","https://openalex.org/W2963280855","https://openalex.org/W2963313316","https://openalex.org/W2963423916","https://openalex.org/W2963430173","https://openalex.org/W2963477884","https://openalex.org/W2963523627","https://openalex.org/W2963614114","https://openalex.org/W2963634205","https://openalex.org/W2963703448","https://openalex.org/W2963864421","https://openalex.org/W2963993537","https://openalex.org/W2964043796","https://openalex.org/W2964161785","https://openalex.org/W2964174623","https://openalex.org/W2964262254","https://openalex.org/W2964309167","https://openalex.org/W2968986602","https://openalex.org/W2971218263","https://openalex.org/W3037590790","https://openalex.org/W3101442004","https://openalex.org/W3103559770","https://openalex.org/W3103780890","https://openalex.org/W3104515094","https://openalex.org/W4241811150","https://openalex.org/W6600002382","https://openalex.org/W6600137863","https://openalex.org/W6600168703","https://openalex.org/W6600446476","https://openalex.org/W6600553734","https://openalex.org/W6601211009","https://openalex.org/W6601870611","https://openalex.org/W6602613565","https://openalex.org/W6602704705","https://openalex.org/W6603727575","https://openalex.org/W6603732165","https://openalex.org/W6605730092","https://openalex.org/W6606825362","https://openalex.org/W6606882031","https://openalex.org/W6608490358","https://openalex.org/W6633651462","https://openalex.org/W6675999342","https://openalex.org/W6676077707","https://openalex.org/W6718092244","https://openalex.org/W6743806954","https://openalex.org/W6746203390","https://openalex.org/W6772334619","https://openalex.org/W6811851346","https://openalex.org/W6814003322","https://openalex.org/W6846889679"],"related_works":["https://openalex.org/W2731899572","https://openalex.org/W2961085424","https://openalex.org/W3215138031","https://openalex.org/W4306674287","https://openalex.org/W3009238340","https://openalex.org/W2939353110","https://openalex.org/W4321369474","https://openalex.org/W4360585206","https://openalex.org/W4285208911","https://openalex.org/W3046775127"],"abstract_inverted_index":{"Deep":[0],"reinforcement":[1],"learning":[2],"(RL)":[3],"has":[4,17],"become":[5],"one":[6],"of":[7],"the":[8,43,74,86],"most":[9],"popular":[10],"topics":[11],"in":[12,21],"artificial":[13],"intelligence":[14],"research.":[15,97],"It":[16],"been":[18],"widely":[19],"used":[20],"various":[22],"fields,":[23],"such":[24],"as":[25],"end-to-end":[26],"control,":[27,29],"robotic":[28],"recommendation":[30],"systems,":[31],"and":[32,47,49,67,80,90],"natural":[33],"language":[34],"dialogue":[35],"systems.":[36],"In":[37],"this":[38],"survey,":[39],"we":[40,84],"systematically":[41],"categorize":[42],"deep":[44,56],"RL":[45,57,69],"algorithms":[46,58],"applications,":[48,89],"provide":[50],"a":[51],"detailed":[52],"review":[53],"over":[54],"existing":[55],"by":[59],"dividing":[60],"them":[61],"into":[62],"modelbased":[63],"methods,":[64,66],"model-free":[65],"advanced":[68],"methods.":[70],"We":[71],"thoroughly":[72],"analyze":[73,91],"advances":[75],"including":[76],"exploration,":[77],"inverse":[78],"RL,":[79],"transfer":[81],"RL.":[82],"Finally,":[83],"outline":[85],"current":[87],"representative":[88],"four":[92],"open":[93],"problems":[94],"for":[95],"future":[96]},"counts_by_year":[{"year":2026,"cited_by_count":13},{"year":2025,"cited_by_count":61},{"year":2024,"cited_by_count":106},{"year":2023,"cited_by_count":47},{"year":2022,"cited_by_count":35},{"year":2021,"cited_by_count":16},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}