{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T23:13:24Z","timestamp":1773962004865,"version":"3.50.1"},"reference-count":55,"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":[{"name":"Major Program of National Natural Science Foundation of China","award":["72192830"],"award-info":[{"award-number":["72192830"]}]},{"name":"Major Program of National Natural Science Foundation of China","award":["72192831"],"award-info":[{"award-number":["72192831"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["72002028"],"award-info":[{"award-number":["72002028"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"111 Project","doi-asserted-by":"publisher","award":["B16009"],"award-info":[{"award-number":["B16009"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Automat. Sci. Eng."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tase.2025.3544431","type":"journal-article","created":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T13:56:13Z","timestamp":1740146173000},"page":"12455-12469","source":"Crossref","is-referenced-by-count":0,"title":["A Combination Feature-Based Reinforcement Learning Approach via Mathematical Optimization"],"prefix":"10.1109","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1689-5473","authenticated-orcid":false,"given":"Fengyuan","family":"Shi","sequence":"first","affiliation":[{"name":"National Frontiers Science Center for Industrial Intelligence and Systems Optimization and the Key Laboratory of Data Analytics and Optimization for Smart Industry, Ministry of Education, Northeastern University, Shenyang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9504-3745","authenticated-orcid":false,"given":"Ying","family":"Meng","sequence":"additional","affiliation":[{"name":"National Frontiers Science Center for Industrial Intelligence and Systems Optimization and the Key Laboratory of Data Analytics and Optimization for Smart Industry, Ministry of Education, Northeastern University, Shenyang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2752-5398","authenticated-orcid":false,"given":"Jiyin","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Business Economics, Loughborough University, Leicestershire, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9950-5169","authenticated-orcid":false,"given":"Lixin","family":"Tang","sequence":"additional","affiliation":[{"name":"National Frontiers Science Center for Industrial Intelligence and Systems Optimization, Northeastern University, Shenyang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1201\/9781439821091"},{"key":"ref2","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref3","doi-asserted-by":"crossref","DOI":"10.1002\/9781118029176","volume-title":"Approximate Dynamic Programming: Solving the Curses of Dimensionality: Second Edition","author":"Powell","year":"2011"},{"key":"ref4","volume-title":"Dynamic Programming and Optimal Control","volume":"1","author":"Bertsekas","year":"2012"},{"key":"ref5","first-page":"1687","volume-title":"Neuro-dynamic ProgrammingNeuro-Dynamic Programming","author":"Bertsekas","year":"2001"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1287\/trsc.1090.0262"},{"key":"ref7","first-page":"695","article-title":"Efficient reinforcement learning with multiple reward functions for randomized controlled trial analysis","volume-title":"Proc. ICML","author":"Lizotte"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2005.1556401"},{"key":"ref9","first-page":"49","article-title":"Least-squares temporal difference learning","volume-title":"Proc. ICML","author":"Boyan"},{"key":"ref10","first-page":"1107","article-title":"Least-squares policy iteration","volume":"4","author":"Lagoudakis","year":"2003","journal-title":"J. Mach. Learn. Res."},{"key":"ref11","first-page":"1","article-title":"Playing Atari with deep reinforcement learning","volume-title":"Proc. NIPS Deep Learn. Workshop","author":"Mnih"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref13","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang"},{"key":"ref14","first-page":"1","article-title":"Prioritized experience replay","volume-title":"Proc. ICLR (Poster)","author":"Schaul"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.1983.6313077"},{"key":"ref16","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mnih"},{"key":"ref17","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proc. 32nd Int. Conf. Int. Conf. Mach. Learn.","volume":"37","author":"Schulman"},{"key":"ref18","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref19","first-page":"1","article-title":"Continuous control with deep reinforcement learning","volume-title":"Proc. ICLR (Poster)","author":"Lillicrap"},{"key":"ref20","first-page":"1352","article-title":"Reinforcement learning with deep energy-based policies","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","author":"Haarnoja"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3080521"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3084198"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3142822"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1111\/itor.12802"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-90421-0_43"},{"issue":"1","key":"ref26","doi-asserted-by":"crossref","first-page":"374","DOI":"10.1016\/j.ejor.2014.03.027","article-title":"Solving real-world cutting stock-problems in the paper industry: Mathematical approaches, experience and challenges","volume":"238","author":"Kallrath","year":"2014","journal-title":"Eur. J. Oper. Res."},{"issue":"1","key":"ref27","doi-asserted-by":"crossref","first-page":"378","DOI":"10.1016\/j.ejor.2020.05.016","article-title":"Solving a large cutting problem in the glass manufacturing industry","volume":"287","author":"Parre\u00f1o","year":"2020","journal-title":"Eur. J. Oper. Res."},{"key":"ref28","doi-asserted-by":"crossref","DOI":"10.1016\/j.ejco.2022.100027","article-title":"A reinforcement learning approach to the stochastic cutting stock problem","volume":"10","author":"Pitombeira-Neto","year":"2022","journal-title":"EURO J. Comput. Optim."},{"key":"ref29","first-page":"2692","article-title":"Pointer networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Vinyals"},{"key":"ref30","first-page":"1","article-title":"Neural combinatorial optimization with reinforcement learning","volume-title":"Workshop Proc. 5th Int. Conf. Learn. Represent.","author":"Bello"},{"key":"ref31","first-page":"1","article-title":"Solving a new 3D bin packing problem with deep reinforcement learning method","volume-title":"Proc. Workshop AI Appl. E-Commerce Co-Located 16th Int. Joint Conf. Artif. Intell.","author":"Hu"},{"key":"ref32","first-page":"1386","article-title":"A multi-task selected learning approach for solving 3D flexible bin packing problem","volume-title":"Proc. 18th Int. Conf. Auto. Agents MultiAgent Syst.","author":"Duan"},{"key":"ref33","first-page":"1","article-title":"Ranked reward: Enabling self-play reinforcement learning for combinatorial optimization","volume-title":"Proc. Workshop Deep Reinforcement Learn. Co-Located 32nd Conf. Adv. Neural Inf. Process. Syst.","author":"Laterre"},{"key":"ref34","first-page":"9861","article-title":"Reinforcement learning for solving the vehicle routing problem","volume-title":"Proc. 32nd Int. Conf. Neural Inf. Process. Syst.","volume":"31","author":"Nazari"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICDMW53433.2021.00042"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3105905"},{"key":"ref37","first-page":"1","article-title":"Combinatorial optimization by graph pointer networks and hierarchical reinforcement learning","volume-title":"Proc. AAAI Workshop Deep Learn. Graphs, Methodologies Appl.","author":"Ma"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403356"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/s42524-020-0126-0"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2022.3165987"},{"key":"ref41","volume-title":"Operations Research an Introduction","author":"Taha","year":"2017"},{"issue":"1","key":"ref42","doi-asserted-by":"crossref","first-page":"157","DOI":"10.2307\/2951479","article-title":"Monotone comparative statics","volume":"62","author":"Milgrom","year":"1994","journal-title":"Econometrica"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1515\/9781400822539"},{"key":"ref44","first-page":"537","article-title":"Combinatorial optimization with graph convolutional networks and guided tree search","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Li"},{"key":"ref45","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Kingma"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2022.3154416"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/BF00226291"},{"issue":"7","key":"ref48","doi-asserted-by":"crossref","first-page":"627","DOI":"10.1016\/S0305-0548(96)00082-2","article-title":"Bison: A fast hybrid procedure for exactly solving the one-dimensional bin packing problem","volume":"24","author":"Scholl","year":"1997","journal-title":"Comput. Operations Res."},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/BF01539705"},{"issue":"5","key":"ref50","first-page":"377","article-title":"The bin-packing problem: A problem generator and some numerical experiments with FFD packing and MTP","volume":"4","author":"Schwerin","year":"1997","journal-title":"Int. Trans. Oper. Res."},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-23480-4_17"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1287\/ijoc.2015.0670"},{"issue":"1","key":"ref53","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.ejor.2016.04.030","article-title":"Bin packing and cutting stock problems: Mathematical models and exact algorithms","volume":"255","author":"Delorme","year":"2016","journal-title":"Eur. J. Oper. Res."},{"issue":"3","key":"ref54","doi-asserted-by":"crossref","first-page":"897","DOI":"10.1016\/j.ejor.2008.04.039","article-title":"The one-dimensional cutting stock problem with usable leftover\u2014A heuristic approach","volume":"196","author":"Cherri","year":"2009","journal-title":"Eur. J. Oper. Res."},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/s11750-021-00611-3"}],"container-title":["IEEE Transactions on Automation Science and Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/8856\/10839176\/10898006.pdf?arnumber=10898006","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T20:10:11Z","timestamp":1773951011000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10898006\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/tase.2025.3544431","relation":{},"ISSN":["1545-5955","1558-3783"],"issn-type":[{"value":"1545-5955","type":"print"},{"value":"1558-3783","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}