{"id":"https://openalex.org/W3094336762","doi":"https://doi.org/10.1109/mlsp49062.2020.9231849","title":"Improving Deep Reinforcement Learning for Financial Trading Using Neural Network Distillation","display_name":"Improving Deep Reinforcement Learning for Financial Trading Using Neural Network Distillation","publication_year":2020,"publication_date":"2020-09-01","ids":{"openalex":"https://openalex.org/W3094336762","doi":"https://doi.org/10.1109/mlsp49062.2020.9231849","mag":"3094336762"},"language":"en","primary_location":{"id":"doi:10.1109/mlsp49062.2020.9231849","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp49062.2020.9231849","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE 30th International Workshop on Machine Learning for Signal Processing (MLSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5056519061","display_name":"Avraam Tsantekidis","orcid":"https://orcid.org/0000-0002-9528-9702"},"institutions":[{"id":"https://openalex.org/I21370196","display_name":"Aristotle University of Thessaloniki","ror":"https://ror.org/02j61yw88","country_code":"GR","type":"education","lineage":["https://openalex.org/I21370196"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Avraam Tsantekidis","raw_affiliation_strings":["School of Informatics, Aristotle University of Thessaloniki, Thessaloniki, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics, Aristotle University of Thessaloniki, Thessaloniki, Greece","institution_ids":["https://openalex.org/I21370196"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061050264","display_name":"Nikolaos Passalis","orcid":"https://orcid.org/0000-0003-1177-9139"},"institutions":[{"id":"https://openalex.org/I21370196","display_name":"Aristotle University of Thessaloniki","ror":"https://ror.org/02j61yw88","country_code":"GR","type":"education","lineage":["https://openalex.org/I21370196"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Nikolaos Passalis","raw_affiliation_strings":["School of Informatics, Aristotle University of Thessaloniki, Thessaloniki, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics, Aristotle University of Thessaloniki, Thessaloniki, Greece","institution_ids":["https://openalex.org/I21370196"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041054091","display_name":"Anastasios Tefas","orcid":"https://orcid.org/0000-0003-1288-3667"},"institutions":[{"id":"https://openalex.org/I21370196","display_name":"Aristotle University of Thessaloniki","ror":"https://ror.org/02j61yw88","country_code":"GR","type":"education","lineage":["https://openalex.org/I21370196"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Anastasios Tefas","raw_affiliation_strings":["School of Informatics, Aristotle University of Thessaloniki, Thessaloniki, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics, Aristotle University of Thessaloniki, Thessaloniki, Greece","institution_ids":["https://openalex.org/I21370196"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I21370196"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"15","issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11326","display_name":"Stock Market Forecasting Methods","score":0.9991000294685364,"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":0.9991000294685364,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9954000115394592,"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/T11052","display_name":"Energy Load and Power Forecasting","score":0.9843999743461609,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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":0.9029027223587036},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7473374605178833},{"id":"https://openalex.org/keywords/foreign-exchange-market","display_name":"Foreign exchange market","score":0.7286538481712341},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6833018064498901},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6369948387145996},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.6092050075531006},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.4430004954338074},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.4255257248878479},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37546807527542114},{"id":"https://openalex.org/keywords/foreign-exchange","display_name":"Foreign exchange","score":0.3006892204284668},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08621662855148315},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.07812830805778503}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9029027223587036},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7473374605178833},{"id":"https://openalex.org/C536366893","wikidata":"https://www.wikidata.org/wiki/Q66076","display_name":"Foreign exchange market","level":3,"score":0.7286538481712341},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6833018064498901},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6369948387145996},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6092050075531006},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.4430004954338074},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.4255257248878479},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37546807527542114},{"id":"https://openalex.org/C2983132609","wikidata":"https://www.wikidata.org/wiki/Q66076","display_name":"Foreign exchange","level":2,"score":0.3006892204284668},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08621662855148315},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.07812830805778503},{"id":"https://openalex.org/C556758197","wikidata":"https://www.wikidata.org/wiki/Q580018","display_name":"Monetary economics","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mlsp49062.2020.9231849","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp49062.2020.9231849","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE 30th International Workshop on Machine Learning for Signal Processing (MLSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/17","score":0.5299999713897705,"display_name":"Partnerships for the goals"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W1191599655","https://openalex.org/W1590184280","https://openalex.org/W1677182931","https://openalex.org/W1757796397","https://openalex.org/W1771410628","https://openalex.org/W1821462560","https://openalex.org/W2046033161","https://openalex.org/W2057884405","https://openalex.org/W2064675550","https://openalex.org/W2095705004","https://openalex.org/W2169015875","https://openalex.org/W2173248099","https://openalex.org/W2173564293","https://openalex.org/W2344786740","https://openalex.org/W2596758708","https://openalex.org/W2735995851","https://openalex.org/W2736601468","https://openalex.org/W2749587125","https://openalex.org/W2749928749","https://openalex.org/W2750784772","https://openalex.org/W2761873684","https://openalex.org/W2768282280","https://openalex.org/W2779040504","https://openalex.org/W2785998551","https://openalex.org/W2885054548","https://openalex.org/W2939856125","https://openalex.org/W2951799221","https://openalex.org/W2953364219","https://openalex.org/W2962515681","https://openalex.org/W2963173418","https://openalex.org/W2963199420","https://openalex.org/W2963313316","https://openalex.org/W2963864421","https://openalex.org/W2964043796","https://openalex.org/W2964291307","https://openalex.org/W4249736682","https://openalex.org/W4298857966","https://openalex.org/W4301761856","https://openalex.org/W6638018090","https://openalex.org/W6674330103","https://openalex.org/W6692846177","https://openalex.org/W6735506055","https://openalex.org/W6743188669","https://openalex.org/W6744838376"],"related_works":["https://openalex.org/W1571781785","https://openalex.org/W1502838439","https://openalex.org/W404327971","https://openalex.org/W4318433428","https://openalex.org/W2562141402","https://openalex.org/W2916737790","https://openalex.org/W4320902972","https://openalex.org/W4380144940","https://openalex.org/W393398260","https://openalex.org/W2135733536"],"abstract_inverted_index":{"Deep":[0],"Reinforcement":[1],"Learning":[2],"(RL)":[3],"is":[4,23,104],"increasingly":[5],"used":[6],"for":[7,12,46,101],"developing":[8],"financial":[9,35,102],"trading":[10,36,103,118],"agents":[11,22],"a":[13,43,67,80,109],"wide":[14],"range":[15],"of":[16,34,92,114],"tasks.":[17],"However,":[18],"optimizing":[19],"deep":[20,48,71,99],"RL":[21,49,58,72,100],"known":[24],"to":[25,52,96],"be":[26],"notoriously":[27],"difficult":[28],"and":[29,55,69,74,82],"unstable,":[30],"hindering":[31],"the":[32,77,93],"performance":[33],"agents.":[37,59],"In":[38],"this":[39],"work,":[40],"we":[41],"propose":[42],"novel":[44],"method":[45,62,95],"training":[47,66],"agents,":[50],"leading":[51],"better":[53],"performing":[54],"more":[56,83],"efficient":[57,84],"The":[60,90],"proposed":[61,94],"works":[63],"by":[64],"first":[65],"large":[68],"complex":[70],"agent":[73,85],"then":[75],"transferring":[76],"knowledge":[78],"into":[79],"smaller":[81],"using":[86,106],"neural":[87],"network":[88],"distillation.":[89],"ability":[91],"significantly":[97],"improve":[98],"demonstrated":[105],"experiments":[107],"on":[108],"time":[110],"series":[111],"dataset":[112],"consisting":[113],"Foreign":[115],"Exchange":[116],"(FOREX)":[117],"pairs":[119],"prices.":[120]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}