{"id":"https://openalex.org/W3213586249","doi":"https://doi.org/10.3390/data6110119","title":"Deep Reinforcement Learning for Trading\u2014A Critical Survey","display_name":"Deep Reinforcement Learning for Trading\u2014A Critical Survey","publication_year":2021,"publication_date":"2021-11-16","ids":{"openalex":"https://openalex.org/W3213586249","doi":"https://doi.org/10.3390/data6110119","mag":"3213586249"},"language":"en","primary_location":{"id":"doi:10.3390/data6110119","is_oa":true,"landing_page_url":"https://doi.org/10.3390/data6110119","pdf_url":"https://www.mdpi.com/2306-5729/6/11/119/pdf?version=1637730378","source":{"id":"https://openalex.org/S4210226510","display_name":"Data","issn_l":"2306-5729","issn":["2306-5729"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2306-5729/6/11/119/pdf?version=1637730378","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079149274","display_name":"Adrian Millea","orcid":null},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Adrian Millea","raw_affiliation_strings":["Imperial College London, London SW7 2AZ, UK"],"affiliations":[{"raw_affiliation_string":"Imperial College London, London SW7 2AZ, UK","institution_ids":["https://openalex.org/I47508984"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5079149274"],"corresponding_institution_ids":["https://openalex.org/I47508984"],"apc_list":{"value":1600,"currency":"CHF","value_usd":1732},"apc_paid":{"value":1600,"currency":"CHF","value_usd":1732},"fwci":3.7677,"has_fulltext":true,"cited_by_count":36,"citation_normalized_percentile":{"value":0.93271504,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"6","issue":"11","first_page":"119","last_page":"119"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11326","display_name":"Stock Market Forecasting Methods","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T11326","display_name":"Stock Market Forecasting Methods","score":0.9994999766349792,"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/T10047","display_name":"Financial Markets and Investment Strategies","score":0.9975000023841858,"subfield":{"id":"https://openalex.org/subfields/2003","display_name":"Finance"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11674","display_name":"Sports Analytics and Performance","score":0.9883000254631042,"subfield":{"id":"https://openalex.org/subfields/2002","display_name":"Economics and Econometrics"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7610315084457397},{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.7111151814460754},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6489260196685791},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.602928102016449},{"id":"https://openalex.org/keywords/cryptocurrency","display_name":"Cryptocurrency","score":0.5572448968887329},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5283936858177185},{"id":"https://openalex.org/keywords/financial-market","display_name":"Financial market","score":0.5258888602256775},{"id":"https://openalex.org/keywords/trading-strategy","display_name":"Trading strategy","score":0.5047351121902466},{"id":"https://openalex.org/keywords/hierarchy","display_name":"Hierarchy","score":0.4897885322570801},{"id":"https://openalex.org/keywords/algorithmic-trading","display_name":"Algorithmic trading","score":0.4678521752357483},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.41976362466812134},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4086553454399109},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3640490770339966},{"id":"https://openalex.org/keywords/finance","display_name":"Finance","score":0.18795064091682434},{"id":"https://openalex.org/keywords/business","display_name":"Business","score":0.14784041047096252},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.111225426197052},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.10471653938293457}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7610315084457397},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.7111151814460754},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6489260196685791},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.602928102016449},{"id":"https://openalex.org/C180706569","wikidata":"https://www.wikidata.org/wiki/Q13479982","display_name":"Cryptocurrency","level":2,"score":0.5572448968887329},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5283936858177185},{"id":"https://openalex.org/C19244329","wikidata":"https://www.wikidata.org/wiki/Q208697","display_name":"Financial market","level":2,"score":0.5258888602256775},{"id":"https://openalex.org/C131562839","wikidata":"https://www.wikidata.org/wiki/Q1574928","display_name":"Trading strategy","level":2,"score":0.5047351121902466},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.4897885322570801},{"id":"https://openalex.org/C78508483","wikidata":"https://www.wikidata.org/wiki/Q139445","display_name":"Algorithmic trading","level":2,"score":0.4678521752357483},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.41976362466812134},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4086553454399109},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3640490770339966},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.18795064091682434},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.14784041047096252},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.111225426197052},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.10471653938293457},{"id":"https://openalex.org/C34447519","wikidata":"https://www.wikidata.org/wiki/Q179522","display_name":"Market economy","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3390/data6110119","is_oa":true,"landing_page_url":"https://doi.org/10.3390/data6110119","pdf_url":"https://www.mdpi.com/2306-5729/6/11/119/pdf?version=1637730378","source":{"id":"https://openalex.org/S4210226510","display_name":"Data","issn_l":"2306-5729","issn":["2306-5729"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:e2617242a51b4451a6674c11d77c1400","is_oa":true,"landing_page_url":"https://doaj.org/article/e2617242a51b4451a6674c11d77c1400","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Data, Vol 6, Iss 11, p 119 (2021)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/2306-5729/6/11/119/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/data6110119","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Data; Volume 6; Issue 11; Pages: 119","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/data6110119","is_oa":true,"landing_page_url":"https://doi.org/10.3390/data6110119","pdf_url":"https://www.mdpi.com/2306-5729/6/11/119/pdf?version=1637730378","source":{"id":"https://openalex.org/S4210226510","display_name":"Data","issn_l":"2306-5729","issn":["2306-5729"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.47999998927116394,"display_name":"Partnerships for the goals","id":"https://metadata.un.org/sdg/17"}],"awards":[{"id":"https://openalex.org/G5201431165","display_name":"EPSRC Centre for Doctoral Training in High Performance Embedded and Distributed Systems","funder_award_id":"EP/L016796/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G5288895031","display_name":null,"funder_award_id":"EPSRC Centre for Doctoral Training","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G6244725262","display_name":null,"funder_award_id":"Centre for Doctoral Training","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G6653872853","display_name":null,"funder_award_id":"EP/L016","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G8895942654","display_name":null,"funder_award_id":"Imperial College","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320320283","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3213586249.pdf","grobid_xml":"https://content.openalex.org/works/W3213586249.grobid-xml"},"referenced_works_count":71,"referenced_works":["https://openalex.org/W1589747210","https://openalex.org/W1934909785","https://openalex.org/W1995236272","https://openalex.org/W2018042870","https://openalex.org/W2024301719","https://openalex.org/W2096446497","https://openalex.org/W2102409316","https://openalex.org/W2140135625","https://openalex.org/W2145339207","https://openalex.org/W2163605009","https://openalex.org/W2185709919","https://openalex.org/W2195085701","https://openalex.org/W2618530766","https://openalex.org/W2745868649","https://openalex.org/W2749604329","https://openalex.org/W2774513877","https://openalex.org/W2799635155","https://openalex.org/W2891295326","https://openalex.org/W2900108799","https://openalex.org/W2904210818","https://openalex.org/W2906216723","https://openalex.org/W2908187187","https://openalex.org/W2910316861","https://openalex.org/W2923023063","https://openalex.org/W2946661738","https://openalex.org/W2948517885","https://openalex.org/W2965771985","https://openalex.org/W2966284335","https://openalex.org/W2967254933","https://openalex.org/W2977551188","https://openalex.org/W2980237409","https://openalex.org/W2982109826","https://openalex.org/W2985815252","https://openalex.org/W2994341146","https://openalex.org/W3011590044","https://openalex.org/W3015954380","https://openalex.org/W3016221005","https://openalex.org/W3017193407","https://openalex.org/W3035574064","https://openalex.org/W3045958001","https://openalex.org/W3085605093","https://openalex.org/W3087349278","https://openalex.org/W3088749011","https://openalex.org/W3089019288","https://openalex.org/W3089914711","https://openalex.org/W3100789280","https://openalex.org/W3104820786","https://openalex.org/W3105931142","https://openalex.org/W3119076796","https://openalex.org/W3124500271","https://openalex.org/W3125919321","https://openalex.org/W3126284633","https://openalex.org/W3126577088","https://openalex.org/W3129190273","https://openalex.org/W3134096209","https://openalex.org/W3136491841","https://openalex.org/W3137745307","https://openalex.org/W3139702805","https://openalex.org/W3149035007","https://openalex.org/W3179456407","https://openalex.org/W4214717370","https://openalex.org/W4229744218","https://openalex.org/W4241584625","https://openalex.org/W4285620138","https://openalex.org/W6654839852","https://openalex.org/W6675401909","https://openalex.org/W6675999342","https://openalex.org/W6684191040","https://openalex.org/W6686239993","https://openalex.org/W6768046647","https://openalex.org/W7038391337"],"related_works":["https://openalex.org/W4313491999","https://openalex.org/W3195402399","https://openalex.org/W2523594540","https://openalex.org/W4206190611","https://openalex.org/W4399587225","https://openalex.org/W4231485458","https://openalex.org/W4386992034","https://openalex.org/W3213042429","https://openalex.org/W2503079957","https://openalex.org/W4400867529"],"abstract_inverted_index":{"Deep":[0],"reinforcement":[1],"learning":[2,11],"(DRL)":[3],"has":[4],"achieved":[5],"significant":[6],"results":[7,170],"in":[8,38,135,160,195],"many":[9],"machine":[10],"(ML)":[12],"benchmarks.":[13],"In":[14,99],"this":[15,163,172],"short":[16,59],"survey,":[17],"we":[18,66,146],"provide":[19,111],"an":[20],"overview":[21],"of":[22,33,52,89,114,118,154,171,193,205],"DRL":[23,156,206],"applied":[24],"to":[25,84,177,188],"trading":[26,40,91],"on":[27],"financial":[28,143],"markets":[29],"with":[30],"the":[31,39,75,90,116,131,137,150,166,169,179,196,203],"purpose":[32],"unravelling":[34],"common":[35,48],"structures":[36],"used":[37,96,141],"community":[41,197],"using":[42,62,81],"DRL,":[43],"as":[44,46,78,80,126],"well":[45,79],"discovering":[47],"issues":[49],"and":[50,106,152,186,202],"limitations":[51],"such":[53,155],"approaches.":[54],"We":[55,133],"include":[56],"also":[57,124],"a":[58,86,112,191],"corpus":[60],"summarization":[61],"Google":[63],"Scholar.":[64],"Moreover,":[65],"discuss":[67,134],"how":[68,190],"one":[69],"can":[70,94,123,198],"use":[71],"hierarchy":[72],"for":[73,97,130,142,149,162,183,208],"dividing":[74],"problem":[76],"space,":[77],"model-based":[82],"RL":[83],"learn":[85],"world":[87],"model":[88],"environment":[92],"which":[93,108,145],"be":[95],"prediction.":[98],"addition,":[100],"multiple":[101],"risk":[102],"measures":[103],"are":[104,174],"defined":[105],"discussed,":[107],"not":[109],"only":[110],"way":[113],"quantifying":[115],"performance":[117],"various":[119,138],"algorithms,":[120],"but":[121],"they":[122],"act":[125],"(dense)":[127],"reward-shaping":[128],"mechanisms":[129],"agent.":[132],"detail":[136],"state":[139],"representations":[140],"markets,":[144],"consider":[147],"critical":[148],"success":[151],"efficiency":[153],"agents.":[157],"The":[158],"market":[159],"focus":[161],"survey":[164,173],"is":[165],"cryptocurrency":[167],"market;":[168],"two-fold:":[175],"firstly,":[176],"find":[178],"most":[180],"promising":[181],"directions":[182],"further":[184],"research":[185,201],"secondly,":[187],"show":[189],"lack":[192],"consistency":[194],"significantly":[199],"impede":[200],"development":[204],"agents":[207],"trading.":[209]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2021-11-22T00:00:00"}