{"id":"https://openalex.org/W4387057251","doi":"https://doi.org/10.3389/frai.2023.1151003","title":"Asynchronous Deep Double Dueling Q-learning for trading-signal execution in limit order book markets","display_name":"Asynchronous Deep Double Dueling Q-learning for trading-signal execution in limit order book markets","publication_year":2023,"publication_date":"2023-09-25","ids":{"openalex":"https://openalex.org/W4387057251","doi":"https://doi.org/10.3389/frai.2023.1151003"},"language":"en","primary_location":{"id":"doi:10.3389/frai.2023.1151003","is_oa":true,"landing_page_url":"https://doi.org/10.3389/frai.2023.1151003","pdf_url":"https://www.frontiersin.org/articles/10.3389/frai.2023.1151003/pdf?isPublishedV2=False","source":{"id":"https://openalex.org/S4210197006","display_name":"Frontiers in Artificial Intelligence","issn_l":"2624-8212","issn":["2624-8212"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.frontiersin.org/articles/10.3389/frai.2023.1151003/pdf?isPublishedV2=False","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081598065","display_name":"Peer Nagy","orcid":"https://orcid.org/0000-0001-7669-481X"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]},{"id":"https://openalex.org/I4210146410","display_name":"Science Oxford","ror":"https://ror.org/04j8yhy50","country_code":"GB","type":"nonprofit","lineage":["https://openalex.org/I4210146410"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Peer Nagy","raw_affiliation_strings":["Department of Engineering Science, Oxford-Man Institute of Quantitative Finance, University of Oxford, Oxford, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Engineering Science, Oxford-Man Institute of Quantitative Finance, University of Oxford, Oxford, United Kingdom","institution_ids":["https://openalex.org/I40120149","https://openalex.org/I4210146410"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039607149","display_name":"Jan-Peter Calliess","orcid":"https://orcid.org/0000-0002-9003-6642"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]},{"id":"https://openalex.org/I4210146410","display_name":"Science Oxford","ror":"https://ror.org/04j8yhy50","country_code":"GB","type":"nonprofit","lineage":["https://openalex.org/I4210146410"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jan-Peter Calliess","raw_affiliation_strings":["Department of Engineering Science, Oxford-Man Institute of Quantitative Finance, University of Oxford, Oxford, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Engineering Science, Oxford-Man Institute of Quantitative Finance, University of Oxford, Oxford, United Kingdom","institution_ids":["https://openalex.org/I40120149","https://openalex.org/I4210146410"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090331439","display_name":"Stefan Zohren","orcid":"https://orcid.org/0000-0002-3392-0394"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]},{"id":"https://openalex.org/I4210128584","display_name":"The Alan Turing Institute","ror":"https://ror.org/035dkdb55","country_code":"GB","type":"facility","lineage":["https://openalex.org/I4210128584"]},{"id":"https://openalex.org/I4210146410","display_name":"Science Oxford","ror":"https://ror.org/04j8yhy50","country_code":"GB","type":"nonprofit","lineage":["https://openalex.org/I4210146410"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Stefan Zohren","raw_affiliation_strings":["Alan Turing Institute, London, United Kingdom","Department of Engineering Science, Oxford-Man Institute of Quantitative Finance, University of Oxford, Oxford, United Kingdom","Man Group, London, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alan Turing Institute, London, United Kingdom","institution_ids":["https://openalex.org/I4210128584"]},{"raw_affiliation_string":"Department of Engineering Science, Oxford-Man Institute of Quantitative Finance, University of Oxford, Oxford, United Kingdom","institution_ids":["https://openalex.org/I40120149","https://openalex.org/I4210146410"]},{"raw_affiliation_string":"Man Group, London, United Kingdom","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5081598065"],"corresponding_institution_ids":["https://openalex.org/I40120149","https://openalex.org/I4210146410"],"apc_list":{"value":1150,"currency":"USD","value_usd":1150},"apc_paid":{"value":1150,"currency":"USD","value_usd":1150},"fwci":2.1583,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.88181818,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"6","issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11326","display_name":"Stock Market Forecasting Methods","score":0.9984999895095825,"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":0.9984999895095825,"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/T11270","display_name":"Complex Systems and Time Series Analysis","score":0.9958000183105469,"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"}},{"id":"https://openalex.org/T10047","display_name":"Financial Markets and Investment Strategies","score":0.9954000115394592,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8297622203826904},{"id":"https://openalex.org/keywords/high-frequency-trading","display_name":"High-frequency trading","score":0.7585952877998352},{"id":"https://openalex.org/keywords/trading-strategy","display_name":"Trading strategy","score":0.7447107434272766},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7188712358474731},{"id":"https://openalex.org/keywords/algorithmic-trading","display_name":"Algorithmic trading","score":0.6560219526290894},{"id":"https://openalex.org/keywords/order-book","display_name":"Order book","score":0.6346222758293152},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6161952018737793},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.5554837584495544},{"id":"https://openalex.org/keywords/limit","display_name":"Limit (mathematics)","score":0.5510408282279968},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.5456346869468689},{"id":"https://openalex.org/keywords/order","display_name":"Order (exchange)","score":0.5291659832000732},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.506447434425354},{"id":"https://openalex.org/keywords/dark-liquidity","display_name":"Dark liquidity","score":0.4888977110385895},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4720388650894165},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4050285816192627},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.1537979543209076},{"id":"https://openalex.org/keywords/financial-economics","display_name":"Financial economics","score":0.14916473627090454},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1316308081150055},{"id":"https://openalex.org/keywords/finance","display_name":"Finance","score":0.1272752285003662},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08169332146644592}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8297622203826904},{"id":"https://openalex.org/C24683644","wikidata":"https://www.wikidata.org/wiki/Q138372","display_name":"High-frequency trading","level":3,"score":0.7585952877998352},{"id":"https://openalex.org/C131562839","wikidata":"https://www.wikidata.org/wiki/Q1574928","display_name":"Trading strategy","level":2,"score":0.7447107434272766},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7188712358474731},{"id":"https://openalex.org/C78508483","wikidata":"https://www.wikidata.org/wiki/Q139445","display_name":"Algorithmic trading","level":2,"score":0.6560219526290894},{"id":"https://openalex.org/C2779309563","wikidata":"https://www.wikidata.org/wiki/Q649206","display_name":"Order book","level":3,"score":0.6346222758293152},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6161952018737793},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.5554837584495544},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.5510408282279968},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.5456346869468689},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.5291659832000732},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.506447434425354},{"id":"https://openalex.org/C11906137","wikidata":"https://www.wikidata.org/wiki/Q1166205","display_name":"Dark liquidity","level":4,"score":0.4888977110385895},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4720388650894165},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4050285816192627},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.1537979543209076},{"id":"https://openalex.org/C106159729","wikidata":"https://www.wikidata.org/wiki/Q2294553","display_name":"Financial economics","level":1,"score":0.14916473627090454},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1316308081150055},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.1272752285003662},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08169332146644592},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3389/frai.2023.1151003","is_oa":true,"landing_page_url":"https://doi.org/10.3389/frai.2023.1151003","pdf_url":"https://www.frontiersin.org/articles/10.3389/frai.2023.1151003/pdf?isPublishedV2=False","source":{"id":"https://openalex.org/S4210197006","display_name":"Frontiers in Artificial Intelligence","issn_l":"2624-8212","issn":["2624-8212"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:0f9348e74457474ba9d2f4e4778cb098","is_oa":true,"landing_page_url":"https://doaj.org/article/0f9348e74457474ba9d2f4e4778cb098","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Frontiers in Artificial Intelligence, Vol 6 (2023)","raw_type":"article"},{"id":"pmh:oai:ora.ox.ac.uk:uuid:0aee1f8f-14db-48e5-b873-64d233fe277e","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306402636","display_name":"Oxford University Research Archive (ORA) (University of Oxford)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I40120149","host_organization_name":"University of Oxford","host_organization_lineage":["https://openalex.org/I40120149"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Symplectic Elements","raw_type":"http://purl.org/coar/resource_type/c_dcae04bc"}],"best_oa_location":{"id":"doi:10.3389/frai.2023.1151003","is_oa":true,"landing_page_url":"https://doi.org/10.3389/frai.2023.1151003","pdf_url":"https://www.frontiersin.org/articles/10.3389/frai.2023.1151003/pdf?isPublishedV2=False","source":{"id":"https://openalex.org/S4210197006","display_name":"Frontiers in Artificial Intelligence","issn_l":"2624-8212","issn":["2624-8212"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/17","score":0.5099999904632568,"display_name":"Partnerships for the goals"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387057251.pdf"},"referenced_works_count":57,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W193250521","https://openalex.org/W656091256","https://openalex.org/W1522301498","https://openalex.org/W1988270113","https://openalex.org/W2076337359","https://openalex.org/W2160519132","https://openalex.org/W2209913494","https://openalex.org/W2596585349","https://openalex.org/W2604272474","https://openalex.org/W2612690371","https://openalex.org/W2736601468","https://openalex.org/W2746553466","https://openalex.org/W2786928559","https://openalex.org/W2885054548","https://openalex.org/W2912823139","https://openalex.org/W2962782348","https://openalex.org/W2963751193","https://openalex.org/W2969477130","https://openalex.org/W2979430717","https://openalex.org/W2979480719","https://openalex.org/W3032916997","https://openalex.org/W3033083249","https://openalex.org/W3034520305","https://openalex.org/W3121195520","https://openalex.org/W3122116365","https://openalex.org/W3122879523","https://openalex.org/W3125789262","https://openalex.org/W3142301639","https://openalex.org/W3159769297","https://openalex.org/W3189099452","https://openalex.org/W3196479566","https://openalex.org/W3207981891","https://openalex.org/W3210007730","https://openalex.org/W4285333865","https://openalex.org/W4287375108","https://openalex.org/W4298857966","https://openalex.org/W4306891359","https://openalex.org/W4323654151","https://openalex.org/W4362722548","https://openalex.org/W4388994527","https://openalex.org/W6631190155","https://openalex.org/W6637967152","https://openalex.org/W6677067356","https://openalex.org/W6678795100","https://openalex.org/W6685444567","https://openalex.org/W6739901393","https://openalex.org/W6741002519","https://openalex.org/W6748554570","https://openalex.org/W6759165585","https://openalex.org/W6761628794","https://openalex.org/W6768482621","https://openalex.org/W6779547475","https://openalex.org/W6780559895","https://openalex.org/W6789378011","https://openalex.org/W6795301340","https://openalex.org/W6854243803"],"related_works":["https://openalex.org/W2553031590","https://openalex.org/W2772541354","https://openalex.org/W2944959808","https://openalex.org/W2782459121","https://openalex.org/W2491678934","https://openalex.org/W2504476032","https://openalex.org/W4246250073","https://openalex.org/W3125310323","https://openalex.org/W4317838017","https://openalex.org/W4387057251"],"abstract_inverted_index":{"We":[0],"employ":[1],"deep":[2],"reinforcement":[3,37],"learning":[4,38],"(RL)":[5],"to":[6,10,45,67,169],"train":[7,61],"an":[8,150],"agent":[9,64,90,148],"successfully":[11],"translate":[12],"a":[13,18,36,47,62,102,117,162],"high-frequency":[14],"trading":[15,19,49,63,70,114,152,165],"signal":[16],"into":[17],"strategy":[20,153,166],"that":[21,65,145,160],"places":[22],"individual":[23],"limit":[24,30,94],"orders.":[25],"Based":[26],"on":[27,55],"the":[28,82,92,108,123,146,170],"ABIDES":[29],"order":[31,57,95,158],"book":[32,58,96],"simulator,":[33],"we":[34,75,121,143],"build":[35],"OpenAI":[39],"gym":[40],"environment":[41,50],"and":[42,101,157],"utilize":[43],"it":[44],"simulate":[46],"realistic":[48],"for":[51,112,154],"NASDAQ":[52],"equities":[53],"based":[54],"historic":[56],"messages.":[59],"To":[60,106],"learns":[66,149],"maximize":[68],"its":[69,98],"return":[71],"in":[72],"this":[73],"environment,":[74],"use":[76],"Deep":[77],"Dueling":[78],"Double":[79],"Q-learning":[80],"with":[81,137],"APEX":[83],"(asynchronous":[84],"prioritized":[85],"experience":[86],"replay)":[87],"architecture.":[88],"The":[89],"observes":[91],"current":[93],"state,":[97],"recent":[99],"history,":[100],"short-term":[103],"directional":[104],"forecast.":[105],"investigate":[107],"performance":[109,124],"of":[110,125,140],"RL":[111,147],"adaptive":[113],"independently":[115],"from":[116],"concrete":[118],"forecasting":[119],"algorithm,":[120],"study":[122],"our":[126],"approach":[127],"utilizing":[128],"synthetic":[129],"alpha":[130],"signals":[131],"obtained":[132],"by":[133],"perturbing":[134],"forward-looking":[135],"returns":[136],"varying":[138],"levels":[139],"noise.":[141],"Here,":[142],"find":[144],"effective":[151],"inventory":[155],"management":[156],"placing":[159],"outperforms":[161],"heuristic":[163],"benchmark":[164],"having":[167],"access":[168],"same":[171],"signal.":[172]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}