{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T11:08:32Z","timestamp":1781521712945,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":37,"publisher":"ACM","funder":[{"name":"UKRI AI World Leading Researcher Fellowship","award":["EP\/W002949\/1"],"award-info":[{"award-number":["EP\/W002949\/1"]}]},{"name":"JPMC Faculty Research Award","award":[""],"award-info":[{"award-number":[""]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,11,15]]},"DOI":"10.1145\/3768292.3770416","type":"proceedings-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T07:24:26Z","timestamp":1763105066000},"page":"18-26","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["JaxMARL-HFT: GPU-Accelerated Large-Scale Multi-Agent Reinforcement Learning for High-Frequency Trading"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6166-2222","authenticated-orcid":false,"given":"Valentin","family":"Mohl","sequence":"first","affiliation":[{"name":"Department of Computer Science, University of Oxford, Oxford, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-6265-9607","authenticated-orcid":false,"given":"Sascha","family":"Frey","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Oxford, Oxford, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-1759-7662","authenticated-orcid":false,"given":"Reuben","family":"Leyland","sequence":"additional","affiliation":[{"name":"Department of Engineering Science, University of Oxford, Oxford, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-7847-9292","authenticated-orcid":false,"given":"Kang","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Statistics, University of Oxford, Oxford, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8935-1146","authenticated-orcid":false,"given":"George","family":"Nigmatulin","sequence":"additional","affiliation":[{"name":"Department of Engineering Science, University of Oxford, Oxford, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8464-2152","authenticated-orcid":false,"given":"Mihai","family":"Cucuringu","sequence":"additional","affiliation":[{"name":"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"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3392-0394","authenticated-orcid":false,"given":"Stefan","family":"Zohren","sequence":"additional","affiliation":[{"name":"Department of Engineering Science, University of Oxford, Oxford, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9688-2498","authenticated-orcid":false,"given":"Jakob","family":"Foerster","sequence":"additional","affiliation":[{"name":"Foerster Lab for AI Research, University of Oxford, Oxford, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2082-734X","authenticated-orcid":false,"given":"Anisoara","family":"Calinescu","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Oxford, Oxford, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,11,14]]},"reference":[{"key":"e_1_3_3_2_2_2","series-title":"(ICAIF \u201921)","volume-title":"Proceedings of the Second ACM International Conference on AI in Finance","author":"Amrouni Selim","year":"2022","unstructured":"Selim Amrouni, Aymeric Moulin, Jared Vann, Svitlana Vyetrenko, Tucker Balch, and Manuela Veloso. 2022. ABIDES-gym: gym environments for multi-agent discrete event simulation and application to financial markets. In Proceedings of the Second ACM International Conference on AI in Finance(ICAIF \u201921)."},{"key":"e_1_3_3_2_3_2","series-title":"(ICAIF \u201921)","volume-title":"Proceedings of the Second ACM International Conference on AI in Finance","author":"Ardon Leo","year":"2022","unstructured":"Leo Ardon, Nelson Vadori, Thomas Spooner, Mengda Xu, Jared Vann, and Sumitra Ganesh. 2022. Towards a fully RL-based market simulator. In Proceedings of the Second ACM International Conference on AI in Finance(ICAIF \u201921)."},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"crossref","unstructured":"Marco Avellaneda and Sasha Stoikov. 2008. High-frequency trading in a limit order book. Quantitative Finance 8 3 (2008) 217\u2013224.","DOI":"10.1080\/14697680701381228"},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-94548-0_4"},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1017\/9781316659335"},{"key":"e_1_3_3_2_7_2","volume-title":"JAX: composable transformations of Python+NumPy programs","author":"Bradbury James","year":"2018","unstructured":"James Bradbury et\u00a0al. 2018. JAX: composable transformations of Python+NumPy programs. http:\/\/github.com\/jax-ml\/jax"},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1145\/3384441.3395986"},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"crossref","unstructured":"Rama Cont and Marvin\u00a0S Muller. 2021. A stochastic partial differential equation model for limit order book dynamics. SIAM Journal on Financial Mathematics 12 2 (2021) 744\u2013787.","DOI":"10.1137\/19M1254489"},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/CIFEr.2012.6327798"},{"key":"e_1_3_3_2_11_2","volume-title":"Forty-second International Conference on Machine Learning","author":"Cusumano-Towner Marco\u00a0Francis","year":"2025","unstructured":"Marco\u00a0Francis Cusumano-Towner et\u00a0al. 2025. Robust Autonomy Emerges from Self-Play. In Forty-second International Conference on Machine Learning. https:\/\/openreview.net\/forum?id=yOXoJpG6Qy"},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"crossref","unstructured":"J\u00a0Doyne Farmer Paolo Patelli and Ilija\u00a0I Zovko. 2005. The predictive power of zero intelligence in financial markets. Proceedings of the National Academy of Sciences 102 6 (2005) 2254\u20132259.","DOI":"10.1073\/pnas.0409157102"},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1145\/3604237.3626880"},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"crossref","unstructured":"Bruno Ga\u0161perov Stjepan Begu\u0161i\u0107 Petra Posedel\u00a0\u0160imovi\u0107 and Zvonko Kostanj\u010dar. 2021. Reinforcement learning approaches to optimal market making. Mathematics 9 21 (2021) 2689.","DOI":"10.3390\/math9212689"},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"crossref","unstructured":"Dhananjay\u00a0K. Gode and Shyam Sunder. 1993. Allocative efficiency of markets with zero-intelligence traders: Market as a partial substitute for individual rationality. Journal of Political Economy 101 1 (1993) 119\u2013137. http:\/\/www.jstor.org\/stable\/2138676","DOI":"10.1086\/261868"},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"crossref","unstructured":"Martin\u00a0D Gould Mason\u00a0A Porter Stacy Williams Mark McDonald Daniel\u00a0J Fenn and Sam\u00a0D Howison. 2013. Limit order books. Quantitative Finance 13 11 (2013) 1709\u20131742.","DOI":"10.1080\/14697688.2013.803148"},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"crossref","unstructured":"Ruihong Huang and Tomas Polak. 2011. LOBSTER: Limit order book reconstruction system. Available at SSRN 1977207 (2011).","DOI":"10.2139\/ssrn.1977207"},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1145\/3383455.3422570"},{"key":"e_1_3_3_2_19_2","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Kazemkhani Saman","year":"2025","unstructured":"Saman Kazemkhani, Aarav Pandya, Daphne Cornelisse, Brennan Shacklett, and Eugene Vinitsky. 2025. GPUDrive: Data-driven, multi-agent driving simulation at 1 million FPS. In The Thirteenth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=ERv8ptegFi"},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-92238-2_53"},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i02.5587"},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"publisher","unstructured":"Johann Lussange et\u00a0al. 2021. Modelling stock markets by multi-agent reinforcement learning. Computational Economics 57 1 (2021) 113\u2013147. 10.1007\/s10614-020-10038-w","DOI":"10.1007\/s10614-020-10038-w"},{"key":"e_1_3_3_2_23_2","unstructured":"Johann Lussange Stefano Vrizzi Stefano Palminteri and Boris Gutkin. 2024. Modelling crypto markets by multi-agent reinforcement learning. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2402.10803 (2024)."},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1145\/3677052.3698639"},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"crossref","unstructured":"Ciamac\u00a0C. Moallemi and Muye Wang. 2022. A reinforcement learning approach to optimal execution. Quantitative Finance 22 6 (2022) 1051\u20131069.","DOI":"10.1080\/14697688.2022.2039403"},{"key":"e_1_3_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1145\/3604237.3626898"},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"crossref","unstructured":"Brian Ning Franco Ho\u00a0Ting Lin and Sebastian Jaimungal. 2021. Double deep q-learning for optimal execution. Applied Mathematical Finance 28 4 (2021) 361\u2013380.","DOI":"10.1080\/1350486X.2022.2077783"},{"key":"e_1_3_3_2_28_2","doi-asserted-by":"crossref","unstructured":"Richard\u00a0G Palmer W\u00a0Brian Arthur John\u00a0H Holland Blake LeBaron and Paul Tayler. 1994. Artificial economic life: a simple model of a stockmarket. Physica D: Nonlinear Phenomena 75 1-3 (1994) 264\u2013274.","DOI":"10.1016\/0167-2789(94)90287-9"},{"key":"e_1_3_3_2_29_2","doi-asserted-by":"crossref","unstructured":"Alexander Rutherford et\u00a0al. 2024. JaxMARL: Multi-agent RL Environments and Algorithms in JAX. Advances in Neural Information Processing Systems 37 (2024) 50925\u201350951.","DOI":"10.52202\/079017-1612"},{"key":"e_1_3_3_2_30_2","doi-asserted-by":"crossref","unstructured":"Brennan Shacklett et\u00a0al. 2023. An Extensible Data-Oriented Architecture for High-Performance Many-World Simulation. ACM Trans. Graph. 42 4 (2023).","DOI":"10.1145\/3592427"},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.5555\/3237383.3237450"},{"key":"e_1_3_3_2_32_2","series-title":"(IJCAI\u201920)","volume-title":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","author":"Spooner Thomas","year":"2021","unstructured":"Thomas Spooner and Rahul Savani. 2021. Robust market making via adversarial reinforcement learning. In Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence(IJCAI\u201920). Article 633, 7\u00a0pages."},{"key":"e_1_3_3_2_33_2","doi-asserted-by":"crossref","unstructured":"Thibaut Th\u00e9ate and Damien Ernst. 2021. An application of deep reinforcement learning to algorithmic trading. Expert systems with applications 173 (2021) 114632.","DOI":"10.1016\/j.eswa.2021.114632"},{"key":"e_1_3_3_2_34_2","doi-asserted-by":"publisher","unstructured":"Nelson Vadori Leo Ardon Sumitra Ganesh Thomas Spooner Selim Amrouni Jared Vann Mengda Xu Zeyu Zheng Tucker Balch and Manuela Veloso. 2024. Towards multi-agent reinforcement learning-driven over-the-counter market simulations. Mathematical Finance 34 2 (2024) 262\u2013347. 10.1111\/mafi.12416","DOI":"10.1111\/mafi.12416"},{"key":"e_1_3_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1145\/3490354.3494448"},{"key":"e_1_3_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1145\/3383455.3422561"},{"key":"e_1_3_3_2_37_2","unstructured":"Jiayi Weng Huayu Chen Dong Yan Kaichao You Alexis Duburcq Minghao Zhang Yi Su Hang Su and Jun Zhu. 2022. Tianshou: A highly modularized deep reinforcement learning library. Journal of Machine Learning Research 23 267 (2022) 1\u20136."},{"key":"e_1_3_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN60899.2024.10650035"}],"event":{"name":"ICAIF '25: 6th ACM International Conference on AI in Finance","location":"Singapore Singapore","acronym":"ICAIF '25"},"container-title":["Proceedings of the 6th ACM International Conference on AI in Finance"],"original-title":[],"deposited":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T07:28:55Z","timestamp":1763105335000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3768292.3770416"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,14]]},"references-count":37,"alternative-id":["10.1145\/3768292.3770416","10.1145\/3768292"],"URL":"https:\/\/doi.org\/10.1145\/3768292.3770416","relation":{},"subject":[],"published":{"date-parts":[[2025,11,14]]},"assertion":[{"value":"2025-11-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}