{"id":"https://openalex.org/W7138418900","doi":"https://doi.org/10.1609/aaai.v40i33.40027","title":"MetaTrader: Learning to Generalize RL Trading Policies Beyond Offline Data","display_name":"MetaTrader: Learning to Generalize RL Trading Policies Beyond Offline Data","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138418900","doi":"https://doi.org/10.1609/aaai.v40i33.40027"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i33.40027","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i33.40027","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i33.40027","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5021233263","display_name":"Haochen Yuan","orcid":"https://orcid.org/0000-0002-7903-8655"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Haochen Yuan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019129747","display_name":"Minting Pan","orcid":"https://orcid.org/0000-0002-4666-510X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Minting Pan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129682720","display_name":"Yunbo Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yunbo Wang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129739372","display_name":"Siyu Gao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Siyu Gao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5129671707","display_name":"Xiaokang Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaokang Yang","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5021233263"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.62626263,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"33","first_page":"28023","last_page":"28031"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.421999990940094,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.421999990940094,"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/T11326","display_name":"Stock Market Forecasting Methods","score":0.3718000054359436,"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/T11413","display_name":"Risk and Portfolio Optimization","score":0.09709999710321426,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/portfolio","display_name":"Portfolio","score":0.6072999835014343},{"id":"https://openalex.org/keywords/core","display_name":"Core (optical fiber)","score":0.5094000101089478},{"id":"https://openalex.org/keywords/online-and-offline","display_name":"Online and offline","score":0.4632999897003174},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4587000012397766},{"id":"https://openalex.org/keywords/stock","display_name":"Stock (firearms)","score":0.4438000023365021},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.37529999017715454},{"id":"https://openalex.org/keywords/portfolio-optimization","display_name":"Portfolio optimization","score":0.3702000081539154}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6771000027656555},{"id":"https://openalex.org/C2780821815","wikidata":"https://www.wikidata.org/wiki/Q5340806","display_name":"Portfolio","level":2,"score":0.6072999835014343},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.5094000101089478},{"id":"https://openalex.org/C2780102126","wikidata":"https://www.wikidata.org/wiki/Q10928179","display_name":"Online and offline","level":2,"score":0.4632999897003174},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4587000012397766},{"id":"https://openalex.org/C204036174","wikidata":"https://www.wikidata.org/wiki/Q909380","display_name":"Stock (firearms)","level":2,"score":0.4438000023365021},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42080000042915344},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39410001039505005},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.37529999017715454},{"id":"https://openalex.org/C202655437","wikidata":"https://www.wikidata.org/wiki/Q7231728","display_name":"Portfolio optimization","level":3,"score":0.3702000081539154},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.3346000015735626},{"id":"https://openalex.org/C74510933","wikidata":"https://www.wikidata.org/wiki/Q1936145","display_name":"Project portfolio management","level":3,"score":0.3163999915122986},{"id":"https://openalex.org/C166052673","wikidata":"https://www.wikidata.org/wiki/Q83021","display_name":"Empirical evidence","level":2,"score":0.2994999885559082},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.28200000524520874},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.28049999475479126},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.2743000090122223},{"id":"https://openalex.org/C131562839","wikidata":"https://www.wikidata.org/wiki/Q1574928","display_name":"Trading strategy","level":2,"score":0.2712000012397766},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.2621000111103058},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2556999921798706}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i33.40027","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i33.40027","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i33.40027","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i33.40027","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1],"(RL)":[2],"has":[3],"shown":[4],"significant":[5],"promise":[6],"in":[7],"sequential":[8],"portfolio":[9,52],"optimization.":[10],"A":[11],"typical":[12],"solution":[13],"involves":[14],"optimizing":[15],"cumulative":[16],"returns":[17],"using":[18],"historical":[19],"offline":[20,39,62,127],"data.":[21,104,128],"However,":[22],"it":[23,73],"may":[24],"produce":[25],"less":[26],"generalizable":[27],"policies":[28],"that":[29,80,95,114,137],"merely":[30],"''memorize''":[31],"optimal":[32],"buying":[33],"and":[34,88,148],"selling":[35],"actions":[36],"from":[37],"the":[38,43,47,84],"data":[40,56,87],"while":[41],"neglecting":[42],"non-stationary":[44],"nature":[45],"of":[46,54,61],"financial":[48],"market.":[49],"We":[50],"frame":[51],"optimization":[53],"stock":[55,86,145],"as":[57],"a":[58,75,96,108,116],"specific":[59],"type":[60],"RL":[63,78],"problem.":[64],"Our":[65],"method,":[66],"MetaTrader,":[67],"presents":[68],"two":[69,132],"key":[70],"contributions.":[71],"First,":[72],"introduces":[74],"novel":[76],"bilevel":[77],"algorithm":[79],"operates":[81],"on":[82,131],"both":[83,143],"original":[85],"its":[89],"transformations.":[90],"The":[91],"core":[92],"idea":[93],"is":[94],"robust":[97],"policy":[98],"should":[99],"generalize":[100],"effectively":[101],"to":[102,121],"out-of-distribution":[103],"Second,":[105],"we":[106],"propose":[107],"new":[109],"temporal":[110],"difference":[111],"(TD)":[112],"method":[113],"leverages":[115],"transformation-based":[117],"conservative":[118],"TD":[119],"target":[120],"address":[122],"value":[123],"overestimation":[124],"under":[125],"limited":[126],"Empirical":[129],"results":[130],"publicly":[133],"available":[134],"datasets":[135],"demonstrate":[136],"MetaTrader":[138],"outperforms":[139],"existing":[140],"methods,":[141],"including":[142],"traditional":[144],"prediction":[146],"models":[147],"RL-based":[149],"trading":[150],"approaches.":[151]},"counts_by_year":[],"updated_date":"2026-03-18T06:31:55.123368","created_date":"2026-03-18T00:00:00"}