{"id":"https://openalex.org/W4414171700","doi":"https://doi.org/10.1007/s10115-025-02562-8","title":"Enhancing deep reinforcement learning for stock trading: a reward shaping approach via expert feedback","display_name":"Enhancing deep reinforcement learning for stock trading: a reward shaping approach via expert feedback","publication_year":2025,"publication_date":"2025-08-14","ids":{"openalex":"https://openalex.org/W4414171700","doi":"https://doi.org/10.1007/s10115-025-02562-8"},"language":"en","primary_location":{"id":"doi:10.1007/s10115-025-02562-8","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10115-025-02562-8","pdf_url":null,"source":{"id":"https://openalex.org/S81770430","display_name":"Knowledge and Information Systems","issn_l":"0219-1377","issn":["0219-1377","0219-3116"],"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":"Knowledge and Information Systems","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":"https://openalex.org/A5070585239","display_name":"Arishi Orra","orcid":null},"institutions":[{"id":"https://openalex.org/I9579091","display_name":"Indian Institute of Technology Mandi","ror":"https://ror.org/05r9r2f34","country_code":"IN","type":"education","lineage":["https://openalex.org/I9579091"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Arishi Orra","raw_affiliation_strings":["School of Mathematical and Statistical Sciences, Indian Institute of Technology Mandi, Mandi, 175005, Himachal Pradesh, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mathematical and Statistical Sciences, Indian Institute of Technology Mandi, Mandi, 175005, Himachal Pradesh, India","institution_ids":["https://openalex.org/I9579091"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079237228","display_name":"Himanshu Choudhary","orcid":"https://orcid.org/0009-0008-3816-1797"},"institutions":[{"id":"https://openalex.org/I9579091","display_name":"Indian Institute of Technology Mandi","ror":"https://ror.org/05r9r2f34","country_code":"IN","type":"education","lineage":["https://openalex.org/I9579091"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Himanshu Choudhary","raw_affiliation_strings":["School of Mathematical and Statistical Sciences, Indian Institute of Technology Mandi, Mandi, 175005, Himachal Pradesh, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mathematical and Statistical Sciences, Indian Institute of Technology Mandi, Mandi, 175005, Himachal Pradesh, India","institution_ids":["https://openalex.org/I9579091"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029125875","display_name":"Ankit Sharma","orcid":"https://orcid.org/0009-0008-9291-7313"},"institutions":[{"id":"https://openalex.org/I9579091","display_name":"Indian Institute of Technology Mandi","ror":"https://ror.org/05r9r2f34","country_code":"IN","type":"education","lineage":["https://openalex.org/I9579091"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Ankit Sharma","raw_affiliation_strings":["School of Mathematical and Statistical Sciences, Indian Institute of Technology Mandi, Mandi, 175005, Himachal Pradesh, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mathematical and Statistical Sciences, Indian Institute of Technology Mandi, Mandi, 175005, Himachal Pradesh, India","institution_ids":["https://openalex.org/I9579091"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015815705","display_name":"Manoj Thakur","orcid":"https://orcid.org/0000-0002-0396-5321"},"institutions":[{"id":"https://openalex.org/I9579091","display_name":"Indian Institute of Technology Mandi","ror":"https://ror.org/05r9r2f34","country_code":"IN","type":"education","lineage":["https://openalex.org/I9579091"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Manoj Thakur","raw_affiliation_strings":["School of Mathematical and Statistical Sciences, Indian Institute of Technology Mandi, Mandi, 175005, Himachal Pradesh, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mathematical and Statistical Sciences, Indian Institute of Technology Mandi, Mandi, 175005, Himachal Pradesh, India","institution_ids":["https://openalex.org/I9579091"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5070585239"],"corresponding_institution_ids":["https://openalex.org/I9579091"],"apc_list":{"value":2890,"currency":"USD","value_usd":2890},"apc_paid":null,"fwci":3.4202,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.92811181,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"67","issue":"11","first_page":"11075","last_page":"11094"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11326","display_name":"Stock Market Forecasting Methods","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9916999936103821,"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/T11052","display_name":"Energy Load and Power Forecasting","score":0.9905999898910522,"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":0.9021000266075134},{"id":"https://openalex.org/keywords/stock-market","display_name":"Stock market","score":0.5246000289916992},{"id":"https://openalex.org/keywords/stock","display_name":"Stock (firearms)","score":0.48350000381469727},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4708999991416931},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.3847000002861023},{"id":"https://openalex.org/keywords/trading-strategy","display_name":"Trading strategy","score":0.34290000796318054},{"id":"https://openalex.org/keywords/empirical-research","display_name":"Empirical research","score":0.3257000148296356}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9021000266075134},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7257999777793884},{"id":"https://openalex.org/C2780299701","wikidata":"https://www.wikidata.org/wiki/Q475000","display_name":"Stock market","level":3,"score":0.5246000289916992},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5029000043869019},{"id":"https://openalex.org/C204036174","wikidata":"https://www.wikidata.org/wiki/Q909380","display_name":"Stock (firearms)","level":2,"score":0.48350000381469727},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4708999991416931},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41519999504089355},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.3847000002861023},{"id":"https://openalex.org/C131562839","wikidata":"https://www.wikidata.org/wiki/Q1574928","display_name":"Trading strategy","level":2,"score":0.34290000796318054},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.3257000148296356},{"id":"https://openalex.org/C77405623","wikidata":"https://www.wikidata.org/wiki/Q598451","display_name":"System dynamics","level":2,"score":0.30390000343322754},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.299699991941452},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.29249998927116394},{"id":"https://openalex.org/C166052673","wikidata":"https://www.wikidata.org/wiki/Q83021","display_name":"Empirical evidence","level":2,"score":0.28610000014305115},{"id":"https://openalex.org/C105002631","wikidata":"https://www.wikidata.org/wiki/Q4833645","display_name":"Subject-matter expert","level":3,"score":0.272599995136261},{"id":"https://openalex.org/C78508483","wikidata":"https://www.wikidata.org/wiki/Q139445","display_name":"Algorithmic trading","level":2,"score":0.27059999108314514},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.2531000077724457}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10115-025-02562-8","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10115-025-02562-8","pdf_url":null,"source":{"id":"https://openalex.org/S81770430","display_name":"Knowledge and Information Systems","issn_l":"0219-1377","issn":["0219-1377","0219-3116"],"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":"Knowledge and Information Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1977051850","https://openalex.org/W1980836123","https://openalex.org/W2025053102","https://openalex.org/W2127152800","https://openalex.org/W2169015875","https://openalex.org/W2286146989","https://openalex.org/W2344786740","https://openalex.org/W2501851833","https://openalex.org/W2625101268","https://openalex.org/W2765302304","https://openalex.org/W2793498167","https://openalex.org/W2811507977","https://openalex.org/W2922995703","https://openalex.org/W2997497843","https://openalex.org/W3016693931","https://openalex.org/W3017229010","https://openalex.org/W3033882778","https://openalex.org/W3035574064","https://openalex.org/W3046559364","https://openalex.org/W3106281374","https://openalex.org/W3203680104","https://openalex.org/W3212614390","https://openalex.org/W4229376254","https://openalex.org/W4248510338","https://openalex.org/W4292242209","https://openalex.org/W4294691400","https://openalex.org/W4306317483","https://openalex.org/W4322747727","https://openalex.org/W4322747749","https://openalex.org/W4367310095","https://openalex.org/W4378875874","https://openalex.org/W4385155145","https://openalex.org/W4387125904","https://openalex.org/W4388664093","https://openalex.org/W4404351504","https://openalex.org/W4410742123"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}
