{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T10:03:42Z","timestamp":1763114622305,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":44,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,11,14]],"date-time":"2024-11-14T00:00:00Z","timestamp":1731542400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,11,14]]},"DOI":"10.1145\/3677052.3698639","type":"proceedings-article","created":{"date-parts":[[2024,11,14]],"date-time":"2024-11-14T06:38:06Z","timestamp":1731566286000},"page":"117-125","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["A Financial Market Simulation Environment for Trading Agents Using Deep Reinforcement Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2099-1414","authenticated-orcid":false,"given":"Chris","family":"Mascioli","sequence":"first","affiliation":[{"name":"University of Michigan, US"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-4675-6233","authenticated-orcid":false,"given":"Anri","family":"Gu","sequence":"additional","affiliation":[{"name":"University of Michigan, US"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7441-0841","authenticated-orcid":false,"given":"Yongzhao","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Liverpool, England"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6501-9827","authenticated-orcid":false,"given":"Mithun","family":"Chakraborty","sequence":"additional","affiliation":[{"name":"University of Michigan, US"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1691-6844","authenticated-orcid":false,"given":"Michael","family":"Wellman","sequence":"additional","affiliation":[{"name":"University of Michigan, US"}]}],"member":"320","published-online":{"date-parts":[[2024,11,14]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3490354.3494433"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3490354.3494372"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/880"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1086\/260062"},{"key":"e_1_3_2_1_5_1","volume-title":"JAX: Composable transformations of Python+NumPy programs","author":"Bradbury James","year":"2018","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_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3384441.3395986"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/1993574.1993622"},{"key":"e_1_3_2_1_8_1","unstructured":"Dave Cliff. 1997. Minimal-intelligence agents for bargaining behaviors in market-based environments. Hewlett-Packard Labs Technical Reports (1997)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2008.907594"},{"key":"e_1_3_2_1_10_1","volume-title":"35th International Conference on Machine Learning. 1407\u20131416","author":"Espeholt Lasse","year":"2018","unstructured":"Lasse Espeholt, Hubert Soyer, Remi Munos, Karen Simonyan, Vlad Mnih, Tom Ward, Yotam Doron, Vlad Firoiu, Tim Harley, Iain Dunning, 2018. IMPALA: Scalable distributed deep-RL with importance weighted actor-learner architectures. In 35th International Conference on Machine Learning. 1407\u20131416."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.0409157102"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3604237.3626880"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1006\/game.1997.0576"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1086\/261868"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jfineco.2008.08.002"},{"key":"e_1_3_2_1_16_1","volume-title":"The Effect of Liquidity on the Spoofability of Financial Markets. In 5th ACM International Conference on AI in Finance.","author":"Gu Anri","year":"2024","unstructured":"Anri Gu, Yongzhao Wang, Chris Mascioli, Mithun Chakraborty, Rahul Savani, Theodore Turocy, and Michael\u00a0P. Wellman. 2024. The Effect of Liquidity on the Spoofability of Financial Markets. In 5th ACM International Conference on AI in Finance."},{"key":"e_1_3_2_1_17_1","volume-title":"32nd International Conference on Machine Learning. PMLR, 805\u2013813","author":"Heinrich Johannes","year":"2015","unstructured":"Johannes Heinrich, Marc Lanctot, and David Silver. 2015. Fictitious self-play in extensive-form games. In 32nd International Conference on Machine Learning. PMLR, 805\u2013813."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"crossref","unstructured":"Konark Jain Nick Firoozye Jonathan Kochems and Philip Treleaven. 2024. Limit order book simulations: A review. Technical Report. University College London. Available at SSRN 4745587.","DOI":"10.2139\/ssrn.4745587"},{"key":"e_1_3_2_1_20_1","unstructured":"Joseph Jerome Leandro S\u00e1nchez-Betancourt Rahul Savani and Martin Herdegen. 2022. Model-based gym environments for limit order book trading. (2022). arxiv:2209.07823"},{"key":"e_1_3_2_1_21_1","volume-title":"6th International Conference on Learning Representations.","author":"Kapturowski Steven","year":"2018","unstructured":"Steven Kapturowski, Georg Ostrovski, John Quan, Remi Munos, and Will Dabney. 2018. Recurrent experience replay in distributed reinforcement learning. In 6th International Conference on Learning Representations."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3383455.3422570"},{"key":"e_1_3_2_1_23_1","unstructured":"Patrick Kidger. 2022. On Neural Differential Equations. (2022). arxiv:2202.02435"},{"key":"e_1_3_2_1_24_1","volume-title":"A unified game-theoretic approach to multiagent reinforcement learning. Advances in Neural Information Processing Systems 30","author":"Lanctot Marc","year":"2017","unstructured":"Marc Lanctot, Vinicius Zambaldi, Audrunas Gruslys, Angeliki Lazaridou, Karl Tuyls, Julien P\u00e9rolat, David Silver, and Thore Graepel. 2017. A unified game-theoretic approach to multiagent reinforcement learning. Advances in Neural Information Processing Systems 30 (2017)."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0165-1889(99)00022-6"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.3390\/jrfm13040071"},{"key":"e_1_3_2_1_27_1","volume-title":"20th International Conference on Machine Learning. PMLR, 536\u2013543","author":"McMahan H\u00a0Brendan","year":"2003","unstructured":"H\u00a0Brendan McMahan, Geoffrey\u00a0J Gordon, and Avrim Blum. 2003. Planning in the presence of cost functions controlled by an adversary. In 20th International Conference on Machine Learning. PMLR, 536\u2013543."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1016\/0167-2789(94)90287-9"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3586183.3606763"},{"key":"e_1_3_2_1_30_1","volume-title":"37th International Conference on Machine Learning. PMLR, 7652\u20137662","author":"Petrenko Aleksei","year":"2020","unstructured":"Aleksei Petrenko, Zhehui Huang, Tushar Kumar, Gaurav Sukhatme, and Vladlen Koltun. 2020. Sample Factory: Egocentric 3D Control from Pixels at 100000 FPS with Asynchronous Reinforcement Learning. In 37th International Conference on Machine Learning. PMLR, 7652\u20137662."},{"volume-title":"5th International Joint Conference on Autonomous Agents and Multi-Agent Systems. Hakodate, 705\u2013712","author":"Phelps S.","key":"e_1_3_2_1_31_1","unstructured":"S. Phelps, M. Marcinkiewicz, S. Parsons, and P. McBurney. 2006. A novel method for automatic strategy acquisition in N-player non-zero-sum games. In 5th International Joint Conference on Autonomous Agents and Multi-Agent Systems. Hakodate, 705\u2013712."},{"volume-title":"8th International Conference on Autonomous Agents and Multi-Agent Systems. 249\u2013256","author":"L.","key":"e_1_3_2_1_32_1","unstructured":"L.\u00a0Julian Schvartzman and Michael\u00a0P. Wellman. 2009. Stronger CDA strategies through empirical game-theoretic analysis and reinforcement learning. In 8th International Conference on Autonomous Agents and Multi-Agent Systems. 249\u2013256."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3604237.3626847"},{"key":"e_1_3_2_1_34_1","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton S.","year":"2018","unstructured":"Richard\u00a0S. Sutton and Andrew\u00a0G. Barto. 2018. Reinforcement Learning: An Introduction (2nd ed.). MIT Press, Cambridge, Massachusetts.","edition":"2"},{"key":"e_1_3_2_1_35_1","volume-title":"14th ACM Conference on Electronic Commerce. 855\u2013872","author":"Wah Elaine","year":"2013","unstructured":"Elaine Wah and Michael\u00a0P. Wellman. 2013. Latency Arbitrage, Market Fragmentation, and Efficiency: A Two-Market Model. In 14th ACM Conference on Electronic Commerce. 855\u2013872."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.5555\/3176788.3176803"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.3390\/g12020046"},{"key":"e_1_3_2_1_38_1","unstructured":"Yongzhao Wang and Michael\u00a0P. Wellman. 2023. Regularization for Strategy Exploration in Empirical Game-Theoretic Analysis. (2023). arxiv:2302.04928"},{"key":"e_1_3_2_1_39_1","volume-title":"International conference on machine learning. PMLR","author":"Wang Ziyu","year":"2016","unstructured":"Ziyu Wang, Tom Schaul, Matteo Hessel, Hado Hasselt, Marc Lanctot, and Nando Freitas. 2016. Dueling network architectures for deep reinforcement learning. In International conference on machine learning. PMLR, 1995\u20132003."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"crossref","unstructured":"Michael\u00a0P. Wellman. 2011. Trading Agents. Morgan and Claypool.","DOI":"10.1007\/978-3-031-01554-0"},{"key":"e_1_3_2_1_41_1","unstructured":"Michael\u00a0P. Wellman Karl Tuyls and Amy Greenwald. 2024. Empirical Game-Theoretic Analysis: A Survey. (2024). arxiv:2403.04018"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.5555\/3237383.3237475"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-9236(98)00060-8"},{"key":"e_1_3_2_1_44_1","volume-title":"Reinforcement Learning in Agent-Based Market Simulation: Unveiling Realistic Stylized Facts and Behavior. arXiv:2403.19781","author":"Yao Zhiyuan","year":"2024","unstructured":"Zhiyuan Yao, Zheng Li, Matthew Thomas, and Ionut Florescu. 2024. Reinforcement Learning in Agent-Based Market Simulation: Unveiling Realistic Stylized Facts and Behavior. arXiv:2403.19781 (2024)."}],"event":{"name":"ICAIF '24: 5th ACM International Conference on AI in Finance","acronym":"ICAIF '24","location":"Brooklyn NY USA"},"container-title":["Proceedings of the 5th ACM International Conference on AI in Finance"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3677052.3698639","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3677052.3698639","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T17:13:16Z","timestamp":1755882796000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3677052.3698639"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,14]]},"references-count":44,"alternative-id":["10.1145\/3677052.3698639","10.1145\/3677052"],"URL":"https:\/\/doi.org\/10.1145\/3677052.3698639","relation":{},"subject":[],"published":{"date-parts":[[2024,11,14]]},"assertion":[{"value":"2024-11-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}