{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T18:10:03Z","timestamp":1755886203918,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":58,"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:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,11,27]]},"DOI":"10.1145\/3604237.3626873","type":"proceedings-article","created":{"date-parts":[[2023,11,25]],"date-time":"2023-11-25T18:09:47Z","timestamp":1700935787000},"page":"619-627","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Mbt-gym: Reinforcement learning for model-based limit order book trading"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8312-0053","authenticated-orcid":false,"given":"Joseph","family":"Jerome","sequence":"first","affiliation":[{"name":"Department of Computer Science, University of Liverpool, United Kingdom"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6447-7105","authenticated-orcid":false,"given":"Leandro","family":"S\u00e1nchez-Betancourt","sequence":"additional","affiliation":[{"name":"Mathematical Institute and Oxford-Man Institute of Quantitative Finance, University of Oxford, United Kingdom"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1262-7831","authenticated-orcid":false,"given":"Rahul","family":"Savani","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Liverpool, United Kingdom and The Alan Turing Institute, United Kingdom"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2092-7167","authenticated-orcid":false,"given":"Martin","family":"Herdegen","sequence":"additional","affiliation":[{"name":"Department of Statistics, University of Warwick, 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":"10.1080\/14697688.2020.1729396"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1137\/090763470"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.21314\/JOR.2001.041"},{"key":"e_1_3_2_1_4_1","volume-title":"ABIDES-Gym: Gym Environments for Multi-Agent Discrete Event Simulation and Application to Financial Markets. arXiv:2110.14771","author":"Amrouni Selim","year":"2021","unstructured":"Selim Amrouni, Aymeric Moulin, Jared Vann, Svitlana Vyetrenko, Tucker Balch, and Manuela Veloso. 2021. ABIDES-Gym: Gym Environments for Multi-Agent Discrete Event Simulation and Application to Financial Markets. arXiv:2110.14771 (2021)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1080\/14697680701381228"},{"key":"e_1_3_2_1_6_1","volume-title":"How to Evaluate Trading Strategies: Single Agent Market Replay or Multiple Agent Interactive Simulation?arXiv:1906.12010","author":"Balch Tucker\u00a0Hybinette","year":"2019","unstructured":"Tucker\u00a0Hybinette Balch, Mahmoud Mahfouz, Joshua Lockhart, Maria Hybinette, and David Byrd. 2019. How to Evaluate Trading Strategies: Single Agent Market Replay or Multiple Agent Interactive Simulation?arXiv:1906.12010 (2019)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1080\/14697688.2020.1766099"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1142\/S0219024918500590"},{"key":"e_1_3_2_1_9_1","volume-title":"Dealing with multi-currency inventory risk in FX cash markets. arXiv preprint arXiv:2207.04100","author":"Barzykin Alexander","year":"2022","unstructured":"Alexander Barzykin, Philippe Bergault, and Olivier Gu\u00e9ant. 2022. Dealing with multi-currency inventory risk in FX cash markets. arXiv preprint arXiv:2207.04100 (2022)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1137\/21M1407756"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/S1386-4181(97)00012-8"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1137\/21M1456467"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1080\/1350486X.2018.1434009"},{"key":"e_1_3_2_1_14_1","volume-title":"Automated Market Makers Designs Beyond Constant Functions. SSRN 4459177","author":"Cartea \u00c1lvaro","year":"2023","unstructured":"\u00c1lvaro Cartea, Fay\u00e7al Drissi, Leandro S\u00e1nchez-Betancourt, David \u0160i\u0161ka, and \u0141ukasz Szpruch. 2023. Automated Market Makers Designs Beyond Constant Functions. SSRN 4459177 (2023)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1080\/14697688.2015.1032543"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11579-016-0162-z"},{"volume-title":"Algorithmic and High-Frequency Trading","author":"Cartea \u00c1lvaro","key":"e_1_3_2_1_17_1","unstructured":"\u00c1lvaro Cartea, Sebastian Jaimungal, and Jos\u00e9 Penalva. 2015. Algorithmic and High-Frequency Trading. Cambridge University Press."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1137\/130911196"},{"volume-title":"Machine Learning and Data Sciences for Financial Markets: A Guide to Contemporary Practices","author":"Cartea \u00c1lvaro","key":"e_1_3_2_1_19_1","unstructured":"\u00c1lvaro Cartea, Sebastian Jaimungal, and Leandro S\u00e1nchez-Betancourt. 2023. Reinforcement Learning for Algorithmic Trading. In Machine Learning and Data Sciences for Financial Markets: A Guide to Contemporary Practices. Cambridge University Press."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00780-022-00491-w"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1142\/S0219024920500168"},{"key":"e_1_3_2_1_22_1","unstructured":"Nicholas\u00a0Tung Chan and Christian Shelton. 2001. An Electronic Market-Maker. (2001)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1287\/opre.1090.0780"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1080\/1350486X.2022.2161588"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1080\/1350486X.2020.1847672"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1080\/14697688.2021.1950919"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1137\/21M1394473"},{"key":"e_1_3_2_1_28_1","volume-title":"Reinforcement Learning for Market Making in a Multi-agent Dealer Market. 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:1911.05892 (2019)."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1080\/14697688.2020.1741670"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3074782"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-9965.2011.00478.x"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1016\/0304-405X(85)90044-3"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1080\/14697688.2013.803148"},{"volume-title":"The Financial Mathematics of Market Liquidity: From Optimal Execution to Market Making","author":"Gueant Olivier","key":"e_1_3_2_1_34_1","unstructured":"Olivier Gueant. 2016. The Financial Mathematics of Market Liquidity: From Optimal Execution to Market Making. Chapman and Hall\/CRC."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11579-012-0087-0"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1080\/14697688.2012.708779"},{"key":"e_1_3_2_1_37_1","volume-title":"Proc. of ICML. 1861\u20131870","author":"Haarnoja Tuomas","year":"2018","unstructured":"Tuomas Haarnoja, Aurick Zhou, Pieter Abbeel, and Sergey Levine. 2018. Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor. In Proc. of ICML. 1861\u20131870."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1016\/0304-405X(81)90020-9"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1214\/21-AAP1672"},{"key":"e_1_3_2_1_40_1","volume-title":"Antonin Raffin, Anssi Kanervisto, and Weixun Wang.","author":"Huang Shengyi","year":"2022","unstructured":"Shengyi Huang, Rousslan Fernand\u00a0Julien Dossa, Antonin Raffin, Anssi Kanervisto, and Weixun Wang. 2022. The 37 Implementation Details of Proximal Policy Optimization. In ICLR Blog Track."},{"key":"e_1_3_2_1_41_1","volume-title":"Market Making with Scaled Beta Policies. arXiv preprint arXiv:2207.03352","author":"Jerome Joseph","year":"2022","unstructured":"Joseph Jerome, Gregory Palmer, and Rahul Savani. 2022. Market Making with Scaled Beta Policies. arXiv preprint arXiv:2207.03352 (2022)."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1137\/19M1259778"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3383455.3422570"},{"key":"e_1_3_2_1_44_1","unstructured":"Adlar\u00a0J Kim and Christian\u00a0R Shelton. 2002. Modeling stock order flows and learning market-making from data. (2002)."},{"key":"e_1_3_2_1_45_1","volume-title":"Proc. of AAMAS. 1892\u20131894","author":"Kumar Pankaj","year":"2020","unstructured":"Pankaj Kumar. 2020. Deep reinforcement learning for market making. In Proc. of AAMAS. 1892\u20131894."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00780-019-00382-7"},{"key":"e_1_3_2_1_47_1","volume-title":"Proc. of ESANN.","author":"Lim Ye-Sheen","year":"2018","unstructured":"Ye-Sheen Lim and Denise Gorse. 2018. Reinforcement Learning for High-Frequency Market Making. In Proc. of ESANN."},{"key":"e_1_3_2_1_48_1","volume-title":"Closed-Loop Nash Competition for Liquidity. arXiv:2112.02961","author":"Micheli Alessandro","year":"2021","unstructured":"Alessandro Micheli, Johannes Muhle-Karbe, and Eyal Neuman. 2021. Closed-Loop Nash Competition for Liquidity. arXiv:2112.02961 (2021)."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1137\/20M1375486"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143929"},{"key":"e_1_3_2_1_51_1","volume-title":"Optimizing Market Making using Multi-Agent Reinforcement Learning. arXiv:1812.10252","author":"Patel Yagna","year":"2018","unstructured":"Yagna Patel. 2018. Optimizing Market Making using Multi-Agent Reinforcement Learning. arXiv:1812.10252 (2018)."},{"key":"e_1_3_2_1_52_1","volume-title":"Deep reinforcement learning in cryptocurrency market making. arXiv:1911.08647","author":"Sadighian Jonathan","year":"2019","unstructured":"Jonathan Sadighian. 2019. Deep reinforcement learning in cryptocurrency market making. arXiv:1911.08647 (2019)."},{"key":"e_1_3_2_1_53_1","volume-title":"Proximal Policy Optimization Algorithms. 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:1707.06347 (2017)."},{"key":"e_1_3_2_1_54_1","volume-title":"Proc. of AAMAS. 434\u2013442","author":"Spooner Thomas","year":"2018","unstructured":"Thomas Spooner, John Fearnley, Rahul Savani, and Andreas Koukorinis. 2018. Market Making via Reinforcement Learning. In Proc. of AAMAS. 434\u2013442."},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/633"},{"key":"e_1_3_2_1_56_1","volume-title":"The NumPy array: a structure for efficient numerical computation. Computing in science & engineering 13, 2","author":"Der\u00a0Walt Stefan Van","year":"2011","unstructured":"Stefan Van Der\u00a0Walt, S\u00a0Chris Colbert, and Gael Varoquaux. 2011. The NumPy array: a structure for efficient numerical computation. Computing in science & engineering 13, 2 (2011), 22\u201330."},{"key":"e_1_3_2_1_57_1","volume-title":"Proc. of AAMAS.","author":"Xu Ziyi","year":"2022","unstructured":"Ziyi Xu, Xue Cheng, and Yangbo He. 2022. Performance of Deep Reinforcement Learning for High Frequency Market Making on Actual Tick Data. In Proc. of AAMAS."},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/615"}],"event":{"name":"ICAIF '23: 4th ACM International Conference on AI in Finance","acronym":"ICAIF '23","location":"Brooklyn NY USA"},"container-title":["4th ACM International Conference on AI in Finance"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3604237.3626873","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3604237.3626873","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T17:38:32Z","timestamp":1755884312000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3604237.3626873"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,25]]},"references-count":58,"alternative-id":["10.1145\/3604237.3626873","10.1145\/3604237"],"URL":"https:\/\/doi.org\/10.1145\/3604237.3626873","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"}}]}}