{"id":"https://openalex.org/W4416232578","doi":"https://doi.org/10.1145/3768292.3770416","title":"JaxMARL-HFT: GPU-Accelerated Large-Scale Multi-Agent Reinforcement Learning for High-Frequency Trading","display_name":"JaxMARL-HFT: GPU-Accelerated Large-Scale Multi-Agent Reinforcement Learning for High-Frequency Trading","publication_year":2025,"publication_date":"2025-11-14","ids":{"openalex":"https://openalex.org/W4416232578","doi":"https://doi.org/10.1145/3768292.3770416"},"language":null,"primary_location":{"id":"doi:10.1145/3768292.3770416","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3768292.3770416","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th 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://doi.org/10.1145/3768292.3770416","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120548879","display_name":"Valentin Mohl","orcid":"https://orcid.org/0000-0002-6166-2222"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Valentin Mohl","raw_affiliation_strings":["Department of Computer Science, University of Oxford, Oxford, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0002-6166-2222","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Oxford, Oxford, United Kingdom","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061498010","display_name":"S. Frey","orcid":"https://orcid.org/0009-0001-6265-9607"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Sascha Frey","raw_affiliation_strings":["Department of Computer Science, University of Oxford, Oxford, United Kingdom"],"raw_orcid":"https://orcid.org/0009-0001-6265-9607","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Oxford, Oxford, United Kingdom","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038679458","display_name":"Reuben Leyland","orcid":"https://orcid.org/0009-0001-1759-7662"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]},{"id":"https://openalex.org/I4210146410","display_name":"Science Oxford","ror":"https://ror.org/04j8yhy50","country_code":"GB","type":"nonprofit","lineage":["https://openalex.org/I4210146410"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Reuben Leyland","raw_affiliation_strings":["Department of Engineering Science, University of Oxford, Oxford, United Kingdom"],"raw_orcid":"https://orcid.org/0009-0001-1759-7662","affiliations":[{"raw_affiliation_string":"Department of Engineering Science, University of Oxford, Oxford, United Kingdom","institution_ids":["https://openalex.org/I4210146410","https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001542402","display_name":"Kang Li","orcid":"https://orcid.org/0009-0007-7847-9292"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Kang Li","raw_affiliation_strings":["Department of Statistics, University of Oxford, Oxford, United Kingdom"],"raw_orcid":"https://orcid.org/0009-0007-7847-9292","affiliations":[{"raw_affiliation_string":"Department of Statistics, University of Oxford, Oxford, United Kingdom","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032875093","display_name":"Georgii Nigmatulin","orcid":"https://orcid.org/0000-0001-8935-1146"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]},{"id":"https://openalex.org/I4210146410","display_name":"Science Oxford","ror":"https://ror.org/04j8yhy50","country_code":"GB","type":"nonprofit","lineage":["https://openalex.org/I4210146410"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"George Nigmatulin","raw_affiliation_strings":["Department of Engineering Science, University of Oxford, Oxford, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0001-8935-1146","affiliations":[{"raw_affiliation_string":"Department of Engineering Science, University of Oxford, Oxford, United Kingdom","institution_ids":["https://openalex.org/I4210146410","https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039600886","display_name":"Mihai Cucuringu","orcid":"https://orcid.org/0000-0002-8464-2152"},"institutions":[{"id":"https://openalex.org/I4210146410","display_name":"Science Oxford","ror":"https://ror.org/04j8yhy50","country_code":"GB","type":"nonprofit","lineage":["https://openalex.org/I4210146410"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mihai Cucuringu","raw_affiliation_strings":["Department of Mathematics, University of California Los Angeles, Los Angeles, USA and Department of Statistics & Oxford Man Institute of Quantitative Finance, University of Oxford, Oxford, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0002-8464-2152","affiliations":[{"raw_affiliation_string":"Department of Mathematics, University of California Los Angeles, Los Angeles, USA and Department of Statistics & Oxford Man Institute of Quantitative Finance, University of Oxford, Oxford, United Kingdom","institution_ids":["https://openalex.org/I4210146410"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090331439","display_name":"Stefan Zohren","orcid":"https://orcid.org/0000-0002-3392-0394"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]},{"id":"https://openalex.org/I4210146410","display_name":"Science Oxford","ror":"https://ror.org/04j8yhy50","country_code":"GB","type":"nonprofit","lineage":["https://openalex.org/I4210146410"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Stefan Zohren","raw_affiliation_strings":["Department of Engineering Science, University of Oxford, Oxford, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0002-3392-0394","affiliations":[{"raw_affiliation_string":"Department of Engineering Science, University of Oxford, Oxford, United Kingdom","institution_ids":["https://openalex.org/I4210146410","https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059094093","display_name":"Jakob Foerster","orcid":"https://orcid.org/0000-0001-9688-2498"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jakob Foerster","raw_affiliation_strings":["Foerster Lab for AI Research, University of Oxford, Oxford, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0001-9688-2498","affiliations":[{"raw_affiliation_string":"Foerster Lab for AI Research, University of Oxford, Oxford, United Kingdom","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020492975","display_name":"Anisoara Calinescu","orcid":"https://orcid.org/0000-0003-2082-734X"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Anisoara Calinescu","raw_affiliation_strings":["Department of Computer Science, University of Oxford, Oxford, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0003-2082-734X","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Oxford, Oxford, United Kingdom","institution_ids":["https://openalex.org/I40120149"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.5123,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.87519816,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"18","last_page":"26"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11326","display_name":"Stock Market Forecasting Methods","score":0.5174999833106995,"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":0.5174999833106995,"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":0.13189999759197235,"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/T11674","display_name":"Sports Analytics and Performance","score":0.07270000129938126,"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":0.8939999938011169},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.6394000053405762},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.6116999983787537},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5903000235557556},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5698000192642212},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.5110999941825867},{"id":"https://openalex.org/keywords/order","display_name":"Order (exchange)","score":0.38830000162124634},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.38499999046325684}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8939999938011169},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7391999959945679},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6394000053405762},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.6116999983787537},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5903000235557556},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5698000192642212},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5453000068664551},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.5110999941825867},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5072000026702881},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.38830000162124634},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.38499999046325684},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3634999990463257},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.35569998621940613},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3264999985694885},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.3160000145435333},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.2987000048160553},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.25870001316070557},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.257999986410141},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.25589999556541443},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.25529998540878296}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3768292.3770416","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3768292.3770416","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th ACM International Conference on AI in Finance","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3768292.3770416","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3768292.3770416","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th ACM International Conference on AI in Finance","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W193250521","https://openalex.org/W2018567859","https://openalex.org/W2032774582","https://openalex.org/W2061165362","https://openalex.org/W2128726101","https://openalex.org/W2162288466","https://openalex.org/W2997874851","https://openalex.org/W3033083249","https://openalex.org/W3034520305","https://openalex.org/W3070092463","https://openalex.org/W3121195520","https://openalex.org/W3122116365","https://openalex.org/W3124184879","https://openalex.org/W3126577088","https://openalex.org/W3168414836","https://openalex.org/W3210221497","https://openalex.org/W4200186852","https://openalex.org/W4206692237","https://openalex.org/W4206757386","https://openalex.org/W4220866459","https://openalex.org/W4245903958","https://openalex.org/W4385282682","https://openalex.org/W4386934282","https://openalex.org/W4388994363","https://openalex.org/W4388994542","https://openalex.org/W4402351331","https://openalex.org/W4404351476","https://openalex.org/W4415797718"],"related_works":[],"abstract_inverted_index":{"Agent-based":[0],"modelling":[1],"(ABM)":[2],"approaches":[3],"for":[4,64,75,120,178,198,232],"high-frequency":[5,76,168],"financial":[6],"markets":[7],"are":[8],"difficult":[9],"to":[10,16,96,125,137,160,171,226],"calibrate":[11],"and":[12,36,87,107,170,180,206,220],"validate,":[13],"partly":[14],"due":[15],"the":[17,38,44,67,84,90,151,162,173,188,233],"large":[18],"parameter":[19],"space":[20],"created":[21],"by":[22],"defining":[23],"fixed":[24],"agent":[25,34],"policies.":[26],"Multi-agent":[27],"reinforcement":[28,72],"learning":[29,73],"(MARL)":[30],"enables":[31,135],"more":[32],"realistic":[33],"behaviour":[35],"reduces":[37],"number":[39],"of":[40,101,190,214],"free":[41],"parameters,":[42],"but":[43],"heavy":[45],"computational":[46],"cost":[47],"has":[48],"so":[49,114],"far":[50],"limited":[51],"research":[52,183],"efforts.":[53],"To":[54],"address":[55],"this,":[56],"we":[57],"introduce":[58],"JaxMARL-HFT":[59,93,191,234],"(JAX-based":[60],"Multi-Agent":[61],"Reinforcement":[62],"Learning":[63],"High-Frequency":[65],"Trading),":[66],"first":[68],"GPU-accelerated":[69],"open-source":[70],"multi-agent":[71],"environment":[74],"trading":[77],"(HFT)":[78],"on":[79,89,150,238],"market-by-order":[80],"(MBO)":[81],"data.":[82],"Extending":[83],"JaxMARL":[85],"framework":[86,235],"building":[88],"JAX-LOB":[91],"implementation,":[92],"is":[94,111,236],"designed":[95,112],"handle":[97],"a":[98,138,199,207],"heterogeneous":[99],"set":[100],"agents,":[102],"enabling":[103],"diverse":[104],"observation/action":[105],"spaces":[106],"reward":[108],"functions.":[109],"It":[110],"flexibly,":[113],"it":[115,158],"can":[116],"also":[117],"be":[118],"used":[119],"single-agent":[121],"RL,":[122],"or":[123],"extended":[124],"act":[126],"as":[127],"an":[128,203],"ABM":[129],"with":[130,146,192,202],"fixed-policy":[131],"agents.":[132],"Leveraging":[133],"JAX":[134],"up":[136],"240x":[139],"reduction":[140],"in":[141,167,184],"end-to-end":[142],"training":[143],"time,":[144],"compared":[145],"state-of-the-art":[147],"reference":[148],"implementations":[149],"same":[152],"hardware.":[153],"This":[154],"significant":[155],"speed-up":[156],"makes":[157],"feasible":[159],"exploit":[161],"large,":[163],"granular":[164],"datasets":[165],"available":[166,237],"trading,":[169],"perform":[172],"extensive":[174],"hyperparameter":[175],"sweeps":[176],"required":[177],"robust":[179],"efficient":[181],"MARL":[182],"trading.":[185],"We":[186],"demonstrate":[187],"use":[189],"independent":[193],"Proximal":[194],"Policy":[195],"Optimization":[196],"(IPPO)":[197],"two-player":[200],"environment,":[201],"order":[204],"execution":[205],"market":[208],"making":[209],"agent,":[210],"using":[211],"one":[212],"year":[213],"LOB":[215],"data":[216],"(400":[217],"million":[218],"orders),":[219],"show":[221],"that":[222],"these":[223],"agents":[224],"learn":[225],"outperform":[227],"standard":[228],"benchmarks.":[229],"The":[230],"code":[231],"GitHub.":[239]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-16T09:24:06.705377","created_date":"2025-11-14T00:00:00"}