{"id":"https://openalex.org/W4391331176","doi":"https://doi.org/10.1109/smc53992.2023.10394135","title":"Automatic Market Making System with Offline Reinforcement Learning","display_name":"Automatic Market Making System with Offline Reinforcement Learning","publication_year":2023,"publication_date":"2023-10-01","ids":{"openalex":"https://openalex.org/W4391331176","doi":"https://doi.org/10.1109/smc53992.2023.10394135"},"language":"en","primary_location":{"id":"doi:10.1109/smc53992.2023.10394135","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/smc53992.2023.10394135","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","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/A5100717686","display_name":"Hong Guo","orcid":"https://orcid.org/0000-0002-4513-8498"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"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":"Hong Guo","raw_affiliation_strings":["Shenzhen International Graduate School, Tsinghua University,Shenzhen,China","Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University,Shenzhen,China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]},{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101429224","display_name":"Yue Zhao","orcid":"https://orcid.org/0000-0003-4022-9208"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"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":"Yue Zhao","raw_affiliation_strings":["Shenzhen International Graduate School, Tsinghua University,Shenzhen,China","Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University,Shenzhen,China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]},{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100635624","display_name":"Jianwu Lin","orcid":"https://orcid.org/0000-0002-0137-451X"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"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":"Jianwu Lin","raw_affiliation_strings":["Shenzhen International Graduate School, Tsinghua University,Shenzhen,China","Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University,Shenzhen,China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]},{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"26","issue":null,"first_page":"3842","last_page":"3847"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11182","display_name":"Auction Theory and Applications","score":0.9966999888420105,"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/T11182","display_name":"Auction Theory and Applications","score":0.9966999888420105,"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":0.9951000213623047,"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":0.991100013256073,"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":0.9610916376113892},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7633018493652344},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.563988983631134},{"id":"https://openalex.org/keywords/online-and-offline","display_name":"Online and offline","score":0.5235828161239624},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.5055174827575684},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4717729091644287},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.42026287317276},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11505457758903503}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9610916376113892},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7633018493652344},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.563988983631134},{"id":"https://openalex.org/C2780102126","wikidata":"https://www.wikidata.org/wiki/Q10928179","display_name":"Online and offline","level":2,"score":0.5235828161239624},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.5055174827575684},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4717729091644287},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.42026287317276},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11505457758903503},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/smc53992.2023.10394135","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/smc53992.2023.10394135","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.5}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2126056473","https://openalex.org/W2133727275","https://openalex.org/W2162288466","https://openalex.org/W2622408375","https://openalex.org/W3022566517","https://openalex.org/W3033324992","https://openalex.org/W3035562414","https://openalex.org/W3124761060","https://openalex.org/W3158302562","https://openalex.org/W3172360140","https://openalex.org/W4385484511","https://openalex.org/W6678795100","https://openalex.org/W6750380350","https://openalex.org/W6756637681","https://openalex.org/W6770543085","https://openalex.org/W6776438516","https://openalex.org/W6779265984","https://openalex.org/W6796589144"],"related_works":["https://openalex.org/W2770234245","https://openalex.org/W96612179","https://openalex.org/W4229499248","https://openalex.org/W2566006169","https://openalex.org/W1567818861","https://openalex.org/W2987774938","https://openalex.org/W4256492088","https://openalex.org/W4310083477","https://openalex.org/W632915154","https://openalex.org/W4225619808"],"abstract_inverted_index":{"Market":[0,10,130],"making":[1,135],"is":[2,38],"an":[3,49],"important":[4],"research":[5],"topic":[6],"in":[7,47,74,96,190,205],"quantitative":[8],"finance.":[9],"makers":[11],"need":[12],"to":[13,21,60,81,86,117,143,182],"continuously":[14],"optimize":[15],"their":[16],"ask":[17],"and":[18,24,140,147,168,193],"bid":[19],"prices":[20],"provide":[22,195],"liquidity":[23],"make":[25],"profits,":[26],"which":[27,48,90,113],"can":[28,71,99],"be":[29,72,92,100],"viewed":[30],"as":[31,76],"a":[32,39,132],"continuous":[33],"control":[34],"problem.":[35],"Reinforcement":[36,127],"learning":[37,69,111,189,204],"common":[40],"method":[41,155],"for":[42,129,199],"solving":[43],"sequential":[44],"decision-making":[45],"problems,":[46],"agent":[50,80,136,160],"learns":[51],"from":[52],"reward":[53],"signals":[54],"through":[55,156],"interactions":[56],"with":[57,83],"the":[58,62,79,84,151,173,180,184,200],"environment":[59,85],"maximize":[61],"cumulative":[63],"return.":[64],"However,":[65],"traditional":[66,166],"online":[67,141,169],"reinforcement":[68,110,188,203],"methods":[70,112],"inefficient":[73],"practice":[75],"they":[77],"require":[78],"interact":[82],"collect":[87],"training":[88,139],"data,":[89],"could":[91],"unstable.":[93],"Additionally,":[94],"exploration":[95],"financial":[97,206],"trading":[98],"very":[101],"expensive.":[102],"To":[103,172],"address":[104],"these":[105],"issues,":[106],"we":[107,123,178,194],"apply":[108],"offline":[109,138,187],"use":[114],"historical":[115],"experience":[116,198],"train":[118],"agents.":[119,171],"In":[120],"this":[121],"paper,":[122],"present":[124],"ORL4MM":[125],"(Offline":[126],"Learning":[128],"Making),":[131],"novel":[133],"market":[134],"using":[137],"fine-tuning":[142],"mitigate":[144],"potential":[145],"losses":[146],"instabilities.":[148],"We":[149],"demonstrate":[150],"effectiveness":[152],"of":[153,175,186,202],"our":[154,159,176],"experiments,":[157],"where":[158],"outperforms":[161],"all":[162],"baseline":[163],"models,":[164],"including":[165],"models":[167],"RL":[170],"best":[174],"knowledge,":[177],"are":[179],"first":[181],"explore":[183],"application":[185],"market-making":[191],"tasks,":[192],"valuable":[196],"practical":[197],"deployment":[201],"scenarios.":[207]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}