{"id":"https://openalex.org/W4404351476","doi":"https://doi.org/10.1145/3677052.3698639","title":"A Financial Market Simulation Environment for Trading Agents Using Deep Reinforcement Learning","display_name":"A Financial Market Simulation Environment for Trading Agents Using Deep Reinforcement Learning","publication_year":2024,"publication_date":"2024-11-14","ids":{"openalex":"https://openalex.org/W4404351476","doi":"https://doi.org/10.1145/3677052.3698639"},"language":"en","primary_location":{"id":"doi:10.1145/3677052.3698639","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3677052.3698639","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3677052.3698639","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th ACM International Conference on AI in Finance","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3677052.3698639","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114637306","display_name":"Chris Mascioli","orcid":"https://orcid.org/0000-0003-2099-1414"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Chris Mascioli","raw_affiliation_strings":["University of Michigan, US"],"raw_orcid":"https://orcid.org/0000-0003-2099-1414","affiliations":[{"raw_affiliation_string":"University of Michigan, US","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114637307","display_name":"Anri Gu","orcid":"https://orcid.org/0009-0003-4675-6233"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anri Gu","raw_affiliation_strings":["University of Michigan, US"],"raw_orcid":"https://orcid.org/0009-0003-4675-6233","affiliations":[{"raw_affiliation_string":"University of Michigan, US","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113306681","display_name":"Yongzhao Wang","orcid":"https://orcid.org/0000-0002-7441-0841"},"institutions":[{"id":"https://openalex.org/I146655781","display_name":"University of Liverpool","ror":"https://ror.org/04xs57h96","country_code":"GB","type":"education","lineage":["https://openalex.org/I146655781"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yongzhao Wang","raw_affiliation_strings":["University of Liverpool, England"],"raw_orcid":"https://orcid.org/0000-0002-7441-0841","affiliations":[{"raw_affiliation_string":"University of Liverpool, England","institution_ids":["https://openalex.org/I146655781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107747807","display_name":"Mithun Chakraborty","orcid":"https://orcid.org/0000-0001-6501-9827"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mithun Chakraborty","raw_affiliation_strings":["University of Michigan, US"],"raw_orcid":"https://orcid.org/0000-0001-6501-9827","affiliations":[{"raw_affiliation_string":"University of Michigan, US","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002102744","display_name":"Michael P. Wellman","orcid":"https://orcid.org/0000-0002-1691-6844"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Wellman","raw_affiliation_strings":["University of Michigan, US"],"raw_orcid":"https://orcid.org/0000-0002-1691-6844","affiliations":[{"raw_affiliation_string":"University of Michigan, US","institution_ids":["https://openalex.org/I27837315"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5114637306"],"corresponding_institution_ids":["https://openalex.org/I27837315"],"apc_list":null,"apc_paid":null,"fwci":9.7355,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.97531592,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"117","last_page":"125"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11270","display_name":"Complex Systems and Time Series Analysis","score":0.9991999864578247,"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"}},"topics":[{"id":"https://openalex.org/T11270","display_name":"Complex Systems and Time Series Analysis","score":0.9991999864578247,"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/T10047","display_name":"Financial Markets and Investment Strategies","score":0.998199999332428,"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/T11326","display_name":"Stock Market Forecasting Methods","score":0.9976000189781189,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8547179698944092},{"id":"https://openalex.org/keywords/financial-market","display_name":"Financial market","score":0.5965520143508911},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4744371473789215},{"id":"https://openalex.org/keywords/algorithmic-trading","display_name":"Algorithmic trading","score":0.47070810198783875},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3050045073032379},{"id":"https://openalex.org/keywords/finance","display_name":"Finance","score":0.30088478326797485},{"id":"https://openalex.org/keywords/business","display_name":"Business","score":0.22204574942588806}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8547179698944092},{"id":"https://openalex.org/C19244329","wikidata":"https://www.wikidata.org/wiki/Q208697","display_name":"Financial market","level":2,"score":0.5965520143508911},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4744371473789215},{"id":"https://openalex.org/C78508483","wikidata":"https://www.wikidata.org/wiki/Q139445","display_name":"Algorithmic trading","level":2,"score":0.47070810198783875},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3050045073032379},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.30088478326797485},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.22204574942588806}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3677052.3698639","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3677052.3698639","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3677052.3698639","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th ACM International Conference on AI in Finance","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3677052.3698639","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3677052.3698639","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3677052.3698639","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th ACM International Conference on AI in Finance","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4404351476.pdf","grobid_xml":"https://content.openalex.org/works/W4404351476.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W2005711429","https://openalex.org/W2018567859","https://openalex.org/W2030478642","https://openalex.org/W2061165362","https://openalex.org/W2064675550","https://openalex.org/W2077791698","https://openalex.org/W2101612387","https://openalex.org/W2123739530","https://openalex.org/W2125907855","https://openalex.org/W2128726101","https://openalex.org/W2786036274","https://openalex.org/W3015681589","https://openalex.org/W3033083249","https://openalex.org/W3034520305","https://openalex.org/W3122786537","https://openalex.org/W3147079603","https://openalex.org/W3165369839","https://openalex.org/W3205386888","https://openalex.org/W3210007730","https://openalex.org/W4214717370","https://openalex.org/W4300222085","https://openalex.org/W4387835442","https://openalex.org/W4388994305","https://openalex.org/W4388994363","https://openalex.org/W4393306226","https://openalex.org/W4401023795"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W3084456289","https://openalex.org/W2182402544","https://openalex.org/W2888943845","https://openalex.org/W4382703609","https://openalex.org/W2969507092","https://openalex.org/W4295539901"],"abstract_inverted_index":{"We":[0,39],"present":[1],"PyMarketSim,":[2],"a":[3,33,118],"financial":[4,136],"market":[5,92,124],"simulation":[6],"environment":[7,22,64],"designed":[8],"for":[9,121],"training":[10],"and":[11,32,43,53,115,130],"evaluating":[12],"trading":[13,71,128],"agents":[14],"using":[15],"deep":[16],"reinforcement":[17],"learning":[18],"(dRL).":[19],"Our":[20,110],"agent-based":[21],"incorporates":[23],"key":[24],"elements":[25],"such":[26],"as":[27,74],"private":[28],"valuations,":[29],"asymmetric":[30],"information,":[31],"flexible":[34],"limit":[35],"order":[36,81],"book":[37],"mechanism.":[38],"demonstrate":[40],"the":[41,95,132],"efficiency":[42],"versatility":[44],"of":[45,107,135],"our":[46,63],"platform":[47],"through":[48],"experiments":[49],"including":[50],"both":[51],"single-agent":[52,58],"multi-agent":[54,96],"dRL":[55],"settings.":[56],"For":[57],"settings,":[59],"we":[60,98],"showcase":[61],"how":[62],"can":[65,85],"be":[66],"used":[67],"to":[68,103],"learn":[69],"background":[70],"strategies":[72],"implemented":[73],"recurrent":[75],"neural":[76],"networks.":[77],"These":[78],"trained":[79],"response":[80],"networks":[82],"(TRON":[83],"agents)":[84],"flexibly":[86],"condition":[87],"their":[88],"behavior":[89],"on":[90],"observed":[91],"characteristics.":[93],"At":[94],"level,":[97],"use":[99],"empirical":[100],"game-theoretic":[101],"techniques":[102],"identify":[104],"equilibrium":[105],"configurations":[106],"TRON":[108],"agents.":[109],"open-source":[111],"implementation":[112],"provides":[113],"researchers":[114],"practitioners":[116],"with":[117],"powerful":[119],"tool":[120],"studying":[122],"complex":[123],"dynamics,":[125],"developing":[126],"advanced":[127],"algorithms,":[129],"exploring":[131],"emergent":[133],"behaviors":[134],"ecosystems":[137],"driven":[138],"by":[139],"machine":[140],"learning.":[141]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}