{"id":"https://openalex.org/W7138363390","doi":"https://doi.org/10.1609/aaai.v40i34.40166","title":"ArchetypeTrader: Reinforcement Learning for Selecting and Refining Learnable Strategic Archetypes in Quantitative Trading","display_name":"ArchetypeTrader: Reinforcement Learning for Selecting and Refining Learnable Strategic Archetypes in Quantitative Trading","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138363390","doi":"https://doi.org/10.1609/aaai.v40i34.40166"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i34.40166","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i34.40166","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/40166/44127","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://ojs.aaai.org/index.php/AAAI/article/download/40166/44127","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129705018","display_name":"Chuqiao Zong","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Chuqiao Zong","raw_affiliation_strings":["Nanyang Technological University"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129684599","display_name":"Molei Qin","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Molei Qin","raw_affiliation_strings":["Nanyang Technological University"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129661253","display_name":"Haochong Xia","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Haochong Xia","raw_affiliation_strings":["Nanyang Technological University"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129642618","display_name":"BO AN","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Bo An","raw_affiliation_strings":["Nanyang Technological University"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5129705018"],"corresponding_institution_ids":["https://openalex.org/I172675005"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.6039604,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"34","first_page":"29269","last_page":"29276"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11326","display_name":"Stock Market Forecasting Methods","score":0.711899995803833,"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":0.711899995803833,"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":0.08839999884366989,"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/T11270","display_name":"Complex Systems and Time Series Analysis","score":0.039400000125169754,"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":0.7856000065803528},{"id":"https://openalex.org/keywords/archetype","display_name":"Archetype","score":0.4853000044822693},{"id":"https://openalex.org/keywords/trading-strategy","display_name":"Trading strategy","score":0.4480000138282776},{"id":"https://openalex.org/keywords/profit","display_name":"Profit (economics)","score":0.39500001072883606},{"id":"https://openalex.org/keywords/algorithmic-trading","display_name":"Algorithmic trading","score":0.3783999979496002},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.34630000591278076},{"id":"https://openalex.org/keywords/soar","display_name":"Soar","score":0.33640000224113464}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7856000065803528},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7448999881744385},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5705999732017517},{"id":"https://openalex.org/C49848784","wikidata":"https://www.wikidata.org/wiki/Q131714","display_name":"Archetype","level":2,"score":0.4853000044822693},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46639999747276306},{"id":"https://openalex.org/C131562839","wikidata":"https://www.wikidata.org/wiki/Q1574928","display_name":"Trading strategy","level":2,"score":0.4480000138282776},{"id":"https://openalex.org/C181622380","wikidata":"https://www.wikidata.org/wiki/Q26911","display_name":"Profit (economics)","level":2,"score":0.39500001072883606},{"id":"https://openalex.org/C78508483","wikidata":"https://www.wikidata.org/wiki/Q139445","display_name":"Algorithmic trading","level":2,"score":0.3783999979496002},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.34630000591278076},{"id":"https://openalex.org/C17305859","wikidata":"https://www.wikidata.org/wiki/Q382944","display_name":"Soar","level":2,"score":0.33640000224113464},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.3224000036716461},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.3091999888420105},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.3041999936103821},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.30399999022483826},{"id":"https://openalex.org/C125308379","wikidata":"https://www.wikidata.org/wiki/Q363057","display_name":"Market segmentation","level":2,"score":0.2824000120162964},{"id":"https://openalex.org/C74072328","wikidata":"https://www.wikidata.org/wiki/Q1142726","display_name":"Intelligent agent","level":2,"score":0.2775999903678894},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.271699994802475},{"id":"https://openalex.org/C189560676","wikidata":"https://www.wikidata.org/wiki/Q1187906","display_name":"Profit margin","level":2,"score":0.27149999141693115}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i34.40166","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i34.40166","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/40166/44127","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.v40i34.40166","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i34.40166","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/40166/44127","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":[{"display_name":"Partnerships for the goals","score":0.40748316049575806,"id":"https://metadata.un.org/sdg/17"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320766","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7138363390.pdf","grobid_xml":"https://content.openalex.org/works/W7138363390.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Quantitative":[0],"trading":[1,10,32,47,155,264,272],"using":[2,58],"mathematical":[3],"models":[4],"and":[5,86,125,133,152,177,218,253,259,262,285],"automated":[6],"execution":[7],"to":[8,65,97,172,183,209,242],"generate":[9,173],"decisions":[11],"has":[12,23],"been":[13],"widely":[14],"applied":[15],"acorss":[16],"financial":[17],"markets.":[18],"Recently,":[19],"reinforcement":[20,146],"learning":[21,124,147],"(RL)":[22],"emerged":[24],"as":[25],"a":[26,144,179,235],"promising":[27],"approach":[28],"for":[29,45,222],"developing":[30],"profitable":[31,261],"strategies,":[33,118],"especially":[34],"in":[35,130,163,281],"highly":[36],"volatile":[37],"markets":[38,57],"like":[39,84],"cryptocurrency.":[40],"However,":[41,69],"existing":[42],"RL":[43,54,94,207],"methods":[44,95],"cryptocurrency":[46,271],"face":[48],"two":[49],"critical":[50],"drawbacks:":[51],"1)":[52,166],"Prior":[53],"algorithms":[55],"segment":[56],"handcrafted":[59],"indicators":[60],"(e.g.,":[61],"trend":[62],"or":[63,116],"volatility)":[64],"train":[66,178,205,234],"specialized":[67],"sub-policies.":[68],"these":[70,139,185],"coarse":[71],"labels":[72],"oversimplify":[73],"market":[74,251],"dynamics":[75],"into":[76,187],"rigid":[77],"categories,":[78],"biasing":[79],"policies":[80],"toward":[81],"obvious":[82],"patterns":[83,198],"trend-following":[85],"neglecting":[87],"nuanced":[88,196],"but":[89],"lucrative":[90],"opportunities.":[91],"2)":[92,202],"Current":[93],"fail":[96],"systematically":[98],"use":[99,168],"demonstration":[100],"data.":[101],"While":[102],"some":[103],"approaches":[104,280],"ignore":[105],"demonstrations":[106,186],"altogether,":[107],"others":[108],"rely":[109],"on":[110,249,268],"\u201coptimal\u201d":[111],"yet":[112],"overly":[113],"granular":[114],"trajectories":[115,176],"human-crafted":[117],"both":[119,282],"of":[120],"which":[121],"can":[122],"overwhelm":[123],"introduce":[126],"significant":[127,134],"bias,":[128],"resulting":[129],"high":[131],"variance":[132],"profit":[135,283],"losses.":[136],"To":[137],"address":[138],"problems,":[140],"we":[141],"propose":[142],"ArchetypeTrader,":[143],"novel":[145],"framework":[148,161],"that":[149,238,275],"automatically":[150],"selects":[151],"refines":[153],"data-driven":[154],"archetypes":[156,191,213],"distilled":[157],"from":[158,214],"demonstrations.":[159],"The":[160],"operates":[162],"three":[164],"phases:":[165],"We":[167,203,232],"dynamic":[169],"programming":[170],"(DP)":[171],"representative":[174],"expert":[175],"vector-quantized":[180],"encoder-decoder":[181],"architecture":[182],"distill":[184],"discrete,":[188],"reusable":[189],"strategic":[190],"through":[192],"self-supervised":[193],"learning,":[194],"capturing":[195],"market-behavior":[197],"without":[199],"human":[200],"heuristics.":[201],"then":[204],"an":[206],"agent":[208],"select":[210],"contextually":[211],"appropriate":[212],"the":[215,223,245],"learned":[216],"codebook":[217],"reconstruct":[219],"action":[220],"sequences":[221],"upcoming":[224],"horizons,":[225],"effectively":[226],"performing":[227],"demonstration-guided":[228],"strategy":[229],"reuse.":[230],"3)":[231],"finally":[233],"policy":[236],"adapter":[237],"leverages":[239],"hindsight-informed":[240],"rewards":[241],"dynamically":[243],"refine":[244],"archetype":[246],"actions":[247],"based":[248],"real-time":[250],"observations":[252],"performance,":[254],"enabling":[255],"more":[256],"fine-grained":[257],"decision-making":[258],"yielding":[260],"robust":[263],"strategies.":[265],"Extensive":[266],"experiments":[267],"four":[269],"popular":[270],"pairs":[273],"demonstrate":[274],"ArchetypeTrader":[276],"significantly":[277],"outperforms":[278],"state-of-the-art":[279],"generation":[284],"risk":[286],"management.":[287]},"counts_by_year":[],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2026-03-18T00:00:00"}