{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T02:04:59Z","timestamp":1771466699387,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":38,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,11,25]],"date-time":"2023-11-25T00:00:00Z","timestamp":1700870400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"UKRI AI World Leading Researcher Fellowship","award":["EP\/W002949\/1"],"award-info":[{"award-number":["EP\/W002949\/1"]}]},{"name":"TAILOR","award":["952215"],"award-info":[{"award-number":["952215"]}]},{"name":"Hasler Foundation","award":["23003"],"award-info":[{"award-number":["23003"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,11,27]]},"DOI":"10.1145\/3604237.3626880","type":"proceedings-article","created":{"date-parts":[[2023,11,25]],"date-time":"2023-11-25T18:09:47Z","timestamp":1700935787000},"page":"583-591","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":8,"title":["JAX-LOB: A GPU-Accelerated limit order book simulator to unlock large scale reinforcement learning for trading"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-6265-9607","authenticated-orcid":false,"given":"Sascha Yves","family":"Frey","sequence":"first","affiliation":[{"name":"Department of Computer Science, University of Oxford, United Kingdom"}]},{"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, United Kingdom"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7669-481X","authenticated-orcid":false,"given":"Peer","family":"Nagy","sequence":"additional","affiliation":[{"name":"Oxford-Man Institute of Quantitative Finance, University of Oxford, United Kingdom"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-0715-983X","authenticated-orcid":false,"given":"Silvia","family":"Sapora","sequence":"additional","affiliation":[{"name":"Foerster Lab for AI Research, University of Oxford, United Kingdom"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-4730-3633","authenticated-orcid":false,"given":"Christopher","family":"Lu","sequence":"additional","affiliation":[{"name":"Foerster Lab for AI Research, University of Oxford, United Kingdom"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3392-0394","authenticated-orcid":false,"given":"Stefan","family":"Zohren","sequence":"additional","affiliation":[{"name":"Oxford-Man Institute of Quantitative Finance, University of Oxford, United Kingdom and Man Group, United Kingdom"}]},{"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, United Kingdom"}]},{"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, United Kingdom"}]}],"member":"320","published-online":{"date-parts":[[2023,11,25]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.21314\/jor.2001.041"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3490354.3494433"},{"key":"e_1_3_2_1_3_1","unstructured":"Igor Babuschkin Kate Baumli Alison Bell Surya Bhupatiraju Jake Bruce Peter Buchlovsky David Budden Trevor Cai Aidan Clark Ivo Danihelka Antoine Dedieu Claudio Fantacci Jonathan Godwin Chris Jones Ross Hemsley Tom Hennigan Matteo Hessel Shaobo Hou Steven Kapturowski Thomas Keck Iurii Kemaev Michael King Markus Kunesch Lena Martens Hamza Merzic Vladimir Mikulik Tamara Norman George Papamakarios John Quan Roman Ring Francisco Ruiz Alvaro Sanchez Rosalia Schneider Eren Sezener Stephen Spencer Srivatsan Srinivasan Wojciech Stokowiec Luyu Wang Guangyao Zhou and Fabio Viola. 2020. The DeepMind JAX Ecosystem. http:\/\/github.com\/deepmind"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-94548-0_4"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/S1386-4181(97)00012-8"},{"key":"e_1_3_2_1_6_1","volume-title":"Market making via reinforcement learning. Applied Reinforcement Learning with Python: With OpenAI Gym, Tensorflow, and Keras","author":"Taweh Taweh","year":"2019","unstructured":"Taweh Beysolow\u00a0II and Taweh Beysolow\u00a0II. 2019. Market making via reinforcement learning. Applied Reinforcement Learning with Python: With OpenAI Gym, Tensorflow, and Keras (2019), 77\u201394."},{"key":"e_1_3_2_1_7_1","volume-title":"Quotes and Prices: Financial Markets Under the Microscope","author":"Bouchaud Jean-Philippe","unstructured":"Jean-Philippe Bouchaud, Julius Bonart, Jonathan Donier, and Martin Gould. 2018. Trades, Quotes and Prices: Financial Markets Under the Microscope. Cambridge University Press. Google-Books-ID: dPRQDwAAQBAJ."},{"key":"e_1_3_2_1_8_1","unstructured":"James Bradbury Roy Frostig Peter Hawkins Matthew\u00a0James Johnson Chris Leary Dougal Maclaurin George Necula Adam Paszke Jake VanderPlas Skye Wanderman-Milne and Qiao Zhang. 2018. JAX: composable transformations of Python+NumPy programs. http:\/\/github.com\/google\/jax"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3384441.3395986"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1137\/16M1058406"},{"key":"e_1_3_2_1_11_1","unstructured":"Philippe Casgrain. 2020. LimitOrderBook.jl. https:\/\/github.com\/p-casgrain\/LimitOrderBook.jl"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1287\/opre.1090.0780"},{"key":"e_1_3_2_1_13_1","volume-title":"Deep execution-value and policy based reinforcement learning for trading and beating market benchmarks. Available at SSRN 3374766","author":"Dab\u00e9rius Kevin","year":"2019","unstructured":"Kevin Dab\u00e9rius, Elvin Granat, and Patrik Karlsson. 2019. Deep execution-value and policy based reinforcement learning for trading and beating market benchmarks. Available at SSRN 3374766 (2019)."},{"key":"e_1_3_2_1_14_1","volume-title":"Imitate then Transcend: Multi-Agent Optimal Execution with Dual-Window Denoise PPO. arXiv preprint arXiv:2206.10736","author":"Fang Jin","year":"2022","unstructured":"Jin Fang, Jiacheng Weng, Yi Xiang, and Xinwen Zhang. 2022. Imitate then Transcend: Multi-Agent Optimal Execution with Dual-Window Denoise PPO. arXiv preprint arXiv:2206.10736 (2022)."},{"key":"e_1_3_2_1_15_1","volume-title":"Reinforcement learning for market making in a multi-agent dealer market. arXiv preprint arXiv:1911.05892","author":"Ganesh Sumitra","year":"2019","unstructured":"Sumitra Ganesh, Nelson Vadori, Mengda Xu, Hua Zheng, Prashant Reddy, and Manuela Veloso. 2019. Reinforcement learning for market making in a multi-agent dealer market. arXiv preprint arXiv:1911.05892 (2019)."},{"key":"e_1_3_2_1_16_1","unstructured":"Google. 23. XLA: Optimizing Compiler for machine learning\u00a0 :\u00a0 tensorflow. https:\/\/www.tensorflow.org\/xla"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1080\/14697688.2013.803148"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.1977207"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3533271.3561745"},{"key":"e_1_3_2_1_20_1","unstructured":"Joseph Jerome Leandro Sanchez-Betancourt Rahul Savani and Martin Herdegen. 2022. Model-based gym environments for limit order book trading. http:\/\/arxiv.org\/abs\/2209.07823 arXiv:2209.07823 [cs q-fin]."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3383455.3422570"},{"key":"e_1_3_2_1_22_1","volume-title":"Adam: A Method for Stochastic Optimization. In International Conference on Learning Representations (ICLR)","author":"Kingma Diederik","year":"2015","unstructured":"Diederik Kingma and Jimmy Ba. 2015. Adam: A Method for Stochastic Optimization. In International Conference on Learning Representations (ICLR). San Diega, CA, USA."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2101784118"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.2307\/1913210"},{"key":"e_1_3_2_1_25_1","unstructured":"Robert\u00a0Tjarko Lange. 2022. gymnax: A JAX-based Reinforcement Learning Environment Library. http:\/\/github.com\/RobertTLange\/gymnax"},{"key":"e_1_3_2_1_26_1","first-page":"16455","article-title":"Discovered policy optimisation","volume":"35","author":"Lu Chris","year":"2022","unstructured":"Chris Lu, Jakub Kuba, Alistair Letcher, Luke Metz, Christian Schroeder\u00a0de Witt, and Jakob Foerster. 2022. Discovered policy optimisation. Advances in Neural Information Processing Systems 35 (2022), 16455\u201316468.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3604237.3626898"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143929"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1080\/1350486X.2022.2077783"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.finmar.2012.09.001"},{"key":"e_1_3_2_1_31_1","unstructured":"James Paulin. 2019. Understanding flash crash contagion and systemic risk: a calibrated agent-based approach. https:\/\/ora.ox.ac.uk\/objects\/uuid:929fa3fe-4e5f-4cef-ad9f-03eb40110818"},{"key":"e_1_3_2_1_32_1","unstructured":"Arnau Quera-Bofarull Joel Dyer Anisoara Calinescu and Michael Wooldridge. 2023. Some challenges of calibrating differentiable agent-based models. http:\/\/arxiv.org\/abs\/2307.01085 arXiv:2307.01085 [cs q-fin stat]."},{"key":"e_1_3_2_1_33_1","volume-title":"Advances in Neural Information Processing Systems, Vol.\u00a033. Curran Associates","author":"Schoenholz S.","year":"2020","unstructured":"Samuel\u00a0S. Schoenholz and Ekin\u00a0D. Cubuk. 2020. JAX M.D. A Framework for Differentiable Physics. In Advances in Neural Information Processing Systems, Vol.\u00a033. Curran Associates, Inc.https:\/\/papers.nips.cc\/paper\/2020\/file\/83d3d4b6c9579515e1679aca8cbc8033-Paper.pdf"},{"key":"e_1_3_2_1_34_1","unstructured":"Maarten Scholl. 2022. Economic Simulation Library."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2015574118"},{"key":"e_1_3_2_1_36_1","volume-title":"Proximal Policy Optimization Algorithms. arXiv preprint arXiv:1707.06347","author":"Schulman John","year":"2017","unstructured":"John Schulman, Filip Wolski, Prafulla Dhariwal, Alec Radford, and Oleg Klimov. 2017. Proximal Policy Optimization Algorithms. arXiv preprint arXiv:1707.06347 (2017)."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3383455.3422561"}],"event":{"name":"ICAIF '23: 4th ACM International Conference on AI in Finance","location":"Brooklyn NY USA","acronym":"ICAIF '23"},"container-title":["4th ACM International Conference on AI in Finance"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3604237.3626880","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3604237.3626880","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T17:37:09Z","timestamp":1755884229000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3604237.3626880"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,25]]},"references-count":38,"alternative-id":["10.1145\/3604237.3626880","10.1145\/3604237"],"URL":"https:\/\/doi.org\/10.1145\/3604237.3626880","relation":{},"subject":[],"published":{"date-parts":[[2023,11,25]]},"assertion":[{"value":"2023-11-25","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}