{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T07:41:22Z","timestamp":1763106082892,"version":"3.45.0"},"publisher-location":"New York, NY, USA","reference-count":35,"publisher":"ACM","funder":[{"name":"UKRI Centre for Doctoral Training in Safe and Trusted Artificial Intelligence","award":["EP\/S023356\/1"],"award-info":[{"award-number":["EP\/S023356\/1"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,11,15]]},"DOI":"10.1145\/3768292.3770396","type":"proceedings-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T07:24:26Z","timestamp":1763105066000},"page":"753-761","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Learning to Scalp: A Reinforcement Learning Agent-Based Study"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-4310-4004","authenticated-orcid":false,"given":"Sriram Bharadwaj","family":"Rangarajan","sequence":"first","affiliation":[{"name":"UKRI Centre for Doctoral Training in Safe and Trusted AI, Department of Informatics, King's College London, London, United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1464-1215","authenticated-orcid":false,"given":"Carmine","family":"Ventre","sequence":"additional","affiliation":[{"name":"Department of Informatics, King's College London, London, United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,11,14]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.5555\/2999792.2999842"},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"crossref","unstructured":"Robert Almgren and Neil Chriss. 2001. Optimal execution of portfolio transactions. Journal of Risk 3 2 (2001) 5\u201339.","DOI":"10.21314\/JOR.2001.041"},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"crossref","unstructured":"Marco Avellaneda and Sasha Stoikov. 2008. High-frequency trading in a limit order book. Quantitative Finance 8 (2008) 217 \u2013 224.","DOI":"10.1080\/14697680701381228"},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"crossref","unstructured":"Dimitris Bertsimas and Andrew\u00a0W. Lo. 1998. Optimal control of execution costs. Journal of Financial Markets 1 1 (1998) 1\u201350.","DOI":"10.1016\/S1386-4181(97)00012-8"},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"crossref","unstructured":"Hendrik Bessembinder Allen Carrion Laura Tuttle and Kumar Venkataraman. 2016. Liquidity resiliency and market quality around predictable trades: Theory and evidence. Journal of Financial Economics 121 1 (2016) 142\u2013166.","DOI":"10.1016\/j.jfineco.2016.02.011"},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1145\/3033274.3085153"},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1145\/3384441.3395986"},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1145\/1993574.1993622"},{"key":"e_1_3_3_1_10_2","volume-title":"An Adaptive Electronic Market-Maker","author":"Chan Nicholas\u00a0T.","year":"2001","unstructured":"Nicholas\u00a0T. Chan and Christian Shelton. 2001. An Adaptive Electronic Market-Maker. Computing in Economics and Finance 2001 146. Society for Computational Economics."},{"key":"e_1_3_3_1_11_2","volume-title":"The Dynamics of Speculative Behaviour","author":"Chiarella Carl","year":"1992","unstructured":"Carl Chiarella. 1992. The Dynamics of Speculative Behaviour. Working Paper Series\u00a013. Finance Discipline Group, UTS Business School, University of Technology, Sydney."},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/CIFEr.2012.6327798"},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"crossref","unstructured":"Wei Cui Anthony Brabazon and Michael O\u2019Neill. 2009. Efficient trade execution using a genetic algorithm in an order book based artificial stock market(GECCO \u201909). Association for Computing Machinery New York NY USA 2023\u20132028.","DOI":"10.1145\/1570256.1570270"},{"key":"e_1_3_3_1_14_2","volume-title":"The Predictive Power of Zero Intelligence in Financial Markets","author":"Farmer J.\u00a0Doyne","year":"2003","unstructured":"J.\u00a0Doyne Farmer, Paolo Patelli, and Ilija\u00a0I. Zovko. 2003. The Predictive Power of Zero Intelligence in Financial Markets. Papers cond-mat\/0309233. arXiv.org."},{"key":"e_1_3_3_1_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.","DOI":"10.1086\/261868"},{"key":"e_1_3_3_1_16_2","unstructured":"Shengyi Huang Rousslan Fernand\u00a0Julien Dossa Chang Ye Jeff Braga Dipam Chakraborty Kinal Mehta and Jo\u00c3\u00a3o\u00a0G.M. Ara\u00c3\u00bajo. 2022. CleanRL: High-quality Single-file Implementations of Deep Reinforcement Learning Algorithms. Journal of Machine Learning Research 23 274 (2022) 1\u201318."},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-61255-9_30"},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.21236\/ADA459806"},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"publisher","unstructured":"King\u2019s College London. 2024. King\u2019s Computational Research Engineering and Technology Environment (CREATE). 10.18742\/rnvf-m076.","DOI":"10.18742\/rnvf-m076"},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"crossref","unstructured":"Mark Kritzman Simon Myrgren and S\u00e9 Page. 2006. Implementation Shortfall. Journal of Portfolio Management 33 1 (Fall 2006) 25\u201330 4.","DOI":"10.3905\/jpm.2006.661367"},{"key":"e_1_3_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.5555\/3535850.3535943"},{"key":"e_1_3_3_1_22_2","volume-title":"Co-existence of Trend and Value in Financial Markets: Estimating an Extended Chiarella Model","author":"Majewski Adam","year":"2018","unstructured":"Adam Majewski, Stefano Ciliberti, and Jean-Philippe Bouchaud. 2018. Co-existence of Trend and Value in Financial Markets: Estimating an Extended Chiarella Model. Papers 1807.11751. arXiv.org."},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"crossref","unstructured":"Anna\u00a0A. Obizhaeva and Jiang Wang. 2013. Optimal trading strategy and supply\/demand dynamics. Journal of Financial Markets 16 1 (2013) 1\u201332.","DOI":"10.1016\/j.finmar.2012.09.001"},{"key":"e_1_3_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/CIFEr.2014.6924049"},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/CIFEr.2012.6327800"},{"key":"e_1_3_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-44871-7_4"},{"key":"e_1_3_3_1_27_2","volume-title":"Market Impact: Empirical Evidence, Theory and Practice","author":"Said Emilio","year":"2022","unstructured":"Emilio Said. 2022. Market Impact: Empirical Evidence, Theory and Practice. Working Papers hal-03668669. HAL."},{"key":"e_1_3_3_1_28_2","doi-asserted-by":"crossref","unstructured":"Mehmet Sa\u00c4\u0178lam. 2020. Order anticipation around predictable trades. Financial Management 49 1 (March 2020) 33\u201367.","DOI":"10.1111\/fima.12255"},{"key":"e_1_3_3_1_29_2","unstructured":"John Schulman Filip Wolski Prafulla Dhariwal Alec Radford and Oleg Klimov. 2017. Proximal Policy Optimization Algorithms. arxiv:https:\/\/arXiv.org\/abs\/1707.06347\u00a0[cs.LG]"},{"key":"e_1_3_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.5555\/3237383.3237450"},{"key":"e_1_3_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557283"},{"key":"e_1_3_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI.2016.7850016"},{"key":"e_1_3_3_1_33_2","doi-asserted-by":"crossref","unstructured":"Vincent Van Kervel and Albert J. Menkveld. 2019. High-Frequency Trading around Large Institutional Orders. Journal of Finance 74 3 (2019) 1091\u20131137.","DOI":"10.1111\/jofi.12759"},{"key":"e_1_3_3_1_34_2","unstructured":"Xintong Wang and Michael\u00a0P. Wellman. 2017. Spoofing the Limit Order Book: An Agent-Based Model(AAMAS \u201917). Richland SC 651\u2013659."},{"key":"e_1_3_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.1145\/3677052.3698623"},{"key":"e_1_3_3_1_36_2","doi-asserted-by":"crossref","unstructured":"Zihao Zhang Bryan Lim and Stefan Zohren. 2021. Deep Learning for Market by Order Data. Applied Mathematical Finance 28 1 (2021) 79\u201395.","DOI":"10.1080\/1350486X.2021.1967767"}],"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":"2025-11-14T07:34:03Z","timestamp":1763105643000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3768292.3770396"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,14]]},"references-count":35,"alternative-id":["10.1145\/3768292.3770396","10.1145\/3768292"],"URL":"https:\/\/doi.org\/10.1145\/3768292.3770396","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"}}]}}