{"id":"https://openalex.org/W4385767666","doi":"https://doi.org/10.24963/ijcai.2023/553","title":"Towards Generalizable Reinforcement Learning for Trade Execution","display_name":"Towards Generalizable Reinforcement Learning for Trade Execution","publication_year":2023,"publication_date":"2023-08-01","ids":{"openalex":"https://openalex.org/W4385767666","doi":"https://doi.org/10.24963/ijcai.2023/553"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2023/553","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/553","pdf_url":"https://www.ijcai.org/proceedings/2023/0553.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2023/0553.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080460228","display_name":"Chuheng Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Chuheng Zhang","raw_affiliation_strings":["Microsoft Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067992353","display_name":"Yitong Duan","orcid":"https://orcid.org/0000-0002-1150-3995"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yitong Duan","raw_affiliation_strings":["Tsinghua University","IIIS, Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"IIIS, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101946507","display_name":"Xiaoyu Chen","orcid":"https://orcid.org/0000-0002-2740-8343"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyu Chen","raw_affiliation_strings":["Tsinghua University","IIIS, Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"IIIS, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100611369","display_name":"Jianyu Chen","orcid":"https://orcid.org/0000-0002-6784-3809"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianyu Chen","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100402538","display_name":"Jian Li","orcid":"https://orcid.org/0000-0002-7725-4346"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Li","raw_affiliation_strings":["Tsinghua University","IIIS, Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"IIIS, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":null,"display_name":"Li Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN","GB"],"is_corresponding":false,"raw_author_name":"Li Zhao","raw_affiliation_strings":["Microsoft Research","IIIS, Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]},{"raw_affiliation_string":"IIIS, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.9106,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.92610907,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"4975","last_page":"4983"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11326","display_name":"Stock Market Forecasting Methods","score":0.9965000152587891,"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":0.9965000152587891,"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/T11182","display_name":"Auction Theory and Applications","score":0.9947999715805054,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9930999875068665,"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/overfitting","display_name":"Overfitting","score":0.9464677572250366},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8419511914253235},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.828697681427002},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6453508734703064},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6406883001327515},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5522609949111938},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.5519173741340637},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.488094687461853},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.4700571298599243},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.22719430923461914},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.08197575807571411}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.9464677572250366},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8419511914253235},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.828697681427002},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6453508734703064},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6406883001327515},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5522609949111938},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.5519173741340637},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.488094687461853},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.4700571298599243},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.22719430923461914},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.08197575807571411},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2023/553","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/553","pdf_url":"https://www.ijcai.org/proceedings/2023/0553.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2023/553","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/553","pdf_url":"https://www.ijcai.org/proceedings/2023/0553.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Partnerships for the goals","score":0.5199999809265137,"id":"https://metadata.un.org/sdg/17"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385767666.pdf","grobid_xml":"https://content.openalex.org/works/W4385767666.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W1988270113","https://openalex.org/W2148176228","https://openalex.org/W2160519132","https://openalex.org/W2338756098","https://openalex.org/W2744628735","https://openalex.org/W2797527950","https://openalex.org/W2803635400","https://openalex.org/W2809668646","https://openalex.org/W2859870583","https://openalex.org/W2898436992","https://openalex.org/W2904489222","https://openalex.org/W2949510923","https://openalex.org/W2969477130","https://openalex.org/W2994073215","https://openalex.org/W2996283175","https://openalex.org/W3035464578","https://openalex.org/W3080373606","https://openalex.org/W3094044532","https://openalex.org/W3128855716","https://openalex.org/W3132558922","https://openalex.org/W3133248211","https://openalex.org/W3213132814","https://openalex.org/W4288287305","https://openalex.org/W4297789758","https://openalex.org/W4302570325"],"related_works":["https://openalex.org/W4362597605","https://openalex.org/W1574414179","https://openalex.org/W4297676672","https://openalex.org/W3009056573","https://openalex.org/W2922073769","https://openalex.org/W4281702477","https://openalex.org/W2490526372","https://openalex.org/W4376166922","https://openalex.org/W4378510483","https://openalex.org/W4221142204"],"abstract_inverted_index":{"Optimized":[0],"trade":[1,32,72,79],"execution":[2,33,80],"is":[3,123],"to":[4,30,34,140,146,180],"sell":[5],"(or":[6],"buy)":[7],"a":[8,14,168,182],"given":[9,15],"amount":[10],"of":[11],"assets":[12],"in":[13,70,105,133,157],"time":[16],"with":[17,84],"the":[18,67,77,89,99,114,120,134,148,191],"lowest":[19],"possible":[20],"trading":[21,100],"cost.":[22],"Recently,":[23],"reinforcement":[24],"learning":[25],"(RL)":[26],"has":[27],"been":[28],"applied":[29],"optimized":[31,71,78],"learn":[35,141],"smarter":[36],"policies":[37],"from":[38,55],"market":[39,92],"data.":[40],"However,":[41],"we":[42,61,75,112,138,165],"find":[43,118],"that":[44,94,119,195],"many":[45],"existing":[46],"RL":[47,83],"methods":[48],"exhibit":[49],"considerable":[50],"overfitting":[51,68,121,149,201],"which":[52],"prevents":[53],"them":[54],"real":[56],"deployment.":[57],"In":[58],"this":[59,110],"paper,":[60],"provide":[62,181],"an":[63,106,158],"extensive":[64],"study":[65],"on":[66,173,190],"problem":[69],"execution.":[73],"First,":[74],"model":[76],"as":[81],"offline":[82,107,135],"dynamic":[85],"context":[86,90,127,131,145],"(ORDC),":[87],"where":[88],"represents":[91],"variables":[93],"cannot":[95],"be":[96],"influenced":[97],"by":[98,125,152],"policy":[101],"and":[102,117,129,202],"are":[103],"collected":[104],"manner.":[108,160],"Under":[109],"framework,":[111],"derive":[113],"generalization":[115],"bound":[116],"issue":[122],"caused":[124],"large":[126],"space":[128],"limited":[130],"samples":[132],"setting.":[136],"Accordingly,":[137],"propose":[139],"compact":[142],"representations":[143],"for":[144,185],"address":[147],"problem,":[150],"either":[151],"leveraging":[153],"prior":[154],"knowledge":[155],"or":[156],"end-to-end":[159],"To":[161],"evaluate":[162],"our":[163,196],"algorithms,":[164],"also":[166],"implement":[167],"carefully":[169],"designed":[170],"simulator":[171,193],"based":[172],"historical":[174],"limit":[175],"order":[176],"book":[177],"(LOB)":[178],"data":[179],"high-fidelity":[183,192],"benchmark":[184],"different":[186],"algorithms.":[187],"Our":[188],"experiments":[189],"demonstrate":[194],"algorithms":[197],"can":[198],"effectively":[199],"alleviate":[200],"achieve":[203],"better":[204],"performance.":[205]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2}],"updated_date":"2026-08-18T07:49:30.821534","created_date":"2025-10-10T00:00:00"}