{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T07:12:43Z","timestamp":1784013163561,"version":"3.55.0"},"reference-count":66,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62272210"],"award-info":[{"award-number":["62272210"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62250710682"],"award-info":[{"award-number":["62250710682"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62331014"],"award-info":[{"award-number":["62331014"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Signal Process."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tsp.2025.3576781","type":"journal-article","created":{"date-parts":[[2025,6,4]],"date-time":"2025-06-04T17:59:14Z","timestamp":1749059954000},"page":"2448-2463","source":"Crossref","is-referenced-by-count":9,"title":["QuantFactor REINFORCE: Mining Steady Formulaic Alpha Factors With Variance-Bounded REINFORCE"],"prefix":"10.1109","volume":"73","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0718-4183","authenticated-orcid":false,"given":"Junjie","family":"Zhao","sequence":"first","affiliation":[{"name":"Guangdong Provincial Key Laboratory of Brain-Inspired Intelligent Computation, Department of Computer Science and Engineering, Department of Statistics and Data Science, Southern University of Science and Technology, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-5876-5632","authenticated-orcid":false,"given":"Chengxi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Modern Physics, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-6316-6125","authenticated-orcid":false,"given":"Min","family":"Qin","sequence":"additional","affiliation":[{"name":"Shenzhen Yujin Hedge Fund Company Ltd., Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5333-6155","authenticated-orcid":false,"given":"Peng","family":"Yang","sequence":"additional","affiliation":[{"name":"Guangdong Provincial Key Laboratory of Brain-Inspired Intelligent Computation, Department of Computer Science and Engineering, Department of Statistics and Data Science, Southern University of Science and Technology, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2024.3495696"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2019.2893862"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2018.2799193"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2019.2907260"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1201\/9781420010794"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2024.3385984"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s12559-023-10179-8"},{"key":"ref8","first-page":"41880","article-title":"OpenFE: Automated feature generation with expert-level performance","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhang","year":"2023"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICSAI57119.2022.10005355"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2022.11.301"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-023-3895-3"},{"key":"ref12","first-page":"507","article-title":"Why do tree-based models still outperform deep learning on typical tabular data?","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Grinsztajn","year":"2022"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.engstruct.2023.116806"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599831"},{"key":"ref15","volume-title":"Markov Decision Processes: Discrete Stochastic Dynamic Programming","author":"Puterman","year":"2014"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.12794\/metadc1505267"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-020-0431-0"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.swevo.2021.100974"},{"key":"ref19","article-title":"Remax: A simple, effective, and efficient method for aligning large language models","author":"Li","year":"2023"},{"key":"ref20","article-title":"Reinforcement-learning connectionist systems","author":"Williams","year":"1987"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3241402"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2025.3542799"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1155\/2018\/3018105"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s11036-017-0962-2"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2020.3027297"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref28","article-title":"Deep reinforcement learning for portfolio management","author":"Huang","year":"2020"},{"key":"ref29","article-title":"Combining reinforcement learning and barrier functions for adaptive risk management in portfolio optimization","author":"Li","year":"2023"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-024-09455-x"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.3737257"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2023.109985"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.118124"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1002\/wilm.10525"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1186\/s13321-021-00575-3"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.3389\/fmed.2021.761050"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.117940"},{"key":"ref38","article-title":"AutoAlpha: An efficient hierarchical evolutionary algorithm for mining alpha factors in quantitative investment","author":"Zhang","year":"2020"},{"key":"ref39","article-title":"Qlib: An AI-oriented quantitative investment platform","author":"Yang","year":"2020"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref41","article-title":"Actor-critic algorithms","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"12","author":"Konda","year":"1999"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-4832-1448-1.50011-1"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17300"},{"key":"ref44","first-page":"7555","article-title":"Leveraging non-uniformity in first-order non-convex optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mei","year":"2021"},{"key":"ref45","first-page":"267","article-title":"Approximately optimal approximate reinforcement learning","volume-title":"Proc. 19th Int. Conf. Mach. Learn.","author":"Kakade","year":"2002"},{"key":"ref46","first-page":"17818","article-title":"The role of baselines in policy gradient optimization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Mei","year":"2022"},{"key":"ref47","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref49","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"Schulman","year":"2015"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-022-10228-y"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.2307\/2333091"},{"key":"ref52","article-title":"Active Portfolio Management: A Quantitative Approach for Producing Superior Returns and Controlling Risk","author":"Grinold","year":"2000"},{"key":"ref53","article-title":"GPLearn: Genetic programming in Python, with a scikit-learn inspired API","author":"Stephens","year":"2024"},{"issue":"268","key":"ref54","first-page":"1","article-title":"Stable-baselines3: Reliable reinforcement learning implementations","volume":"22","author":"Raffin","year":"2021","journal-title":"J. Mach. Learn. Res."},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1038\/323533a0"},{"key":"ref56","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Schulman","year":"2015"},{"key":"ref57","article-title":"Asynchronous methods for deep reinforcement learning","author":"Mnih","year":"2016"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-78676-1_11"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1093\/rfs\/hhu032"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbankfin.2007.09.023"},{"key":"ref61","article-title":"Alleviating non-identifiability: A high-fidelity calibration objective for financial market simulation with multivariate time series data","author":"Wang","year":"2024"},{"key":"ref62","article-title":"SimLOB: Learning representations of limited order book for financial market simulation","author":"Li","year":"2024"},{"key":"ref63","article-title":"China index research","author":"Zhang","year":"2022"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2021.3083985"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-022-0277-5"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1186\/s13634-018-0542-z"}],"container-title":["IEEE Transactions on Signal Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/78\/10807692\/11024173.pdf?arnumber=11024173","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,4]],"date-time":"2025-07-04T17:53:04Z","timestamp":1751651584000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11024173\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":66,"URL":"https:\/\/doi.org\/10.1109\/tsp.2025.3576781","relation":{},"ISSN":["1053-587X","1941-0476"],"issn-type":[{"value":"1053-587X","type":"print"},{"value":"1941-0476","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}