{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,20]],"date-time":"2025-12-20T22:31:38Z","timestamp":1766269898173,"version":"3.40.1"},"reference-count":50,"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","72192831"],"award-info":[{"award-number":["72192830","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.2024.3456074","type":"journal-article","created":{"date-parts":[[2024,9,16]],"date-time":"2024-09-16T18:25:02Z","timestamp":1726511102000},"page":"6860-6875","source":"Crossref","is-referenced-by-count":1,"title":["Tree Search Reinforcement Learning for Two-Dimensional Cutting Stock Problem With Complex Constraints"],"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, Northeastern University, Shenyang, China"}],"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":"10.1287\/mnsc.6.4.366"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1287\/opre.9.6.849"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1287\/opre.11.6.863"},{"issue":"2","key":"ref4","doi-asserted-by":"crossref","first-page":"197","DOI":"10.1016\/0377-2217(90)90355-F","article-title":"Optimal solutions for the cutting stock problem","volume":"44","author":"Goulimis","year":"1990","journal-title":"Eur. J. Oper. Res."},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1080\/00207540903317523"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1361\/10599490523968"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMECH.2019.2899365"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3055499"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3103811"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3105232"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s42524-020-0126-0"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3207011"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2022.3167380"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2023.3282313"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2022.3222314"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref17","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","volume-title":"Proc. Int. Conf. Int. Conf. Mach. Learn.","volume":"48","author":"Wang"},{"key":"ref18","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume-title":"Proc. 12th Int. Conf. Neural Inf. Process. Syst.","author":"Sutton"},{"key":"ref19","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc. 33rd Int. Conf. Int. Conf. Mach. Learn.","volume":"48","author":"Mnih"},{"key":"ref20","first-page":"1","article-title":"Continuous control with deep reinforcement learning","volume-title":"Proc. ICLR","author":"Lillicrap"},{"key":"ref21","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref22","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":"ref23","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":"ref24","first-page":"1","article-title":"Neural combinatorial optimization with reinforcement learning","volume-title":"Proc. 5th Int. Conf. Learn. Represent.","author":"Bello"},{"key":"ref25","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":"ref26","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":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.cor.2021.105400"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2020.07.063"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/614"},{"key":"ref30","first-page":"9861","article-title":"Reinforcement learning for solving the vehicle routing problem","volume-title":"Proc. 32nd Int. Conf. Neural Inf. Process. Syst.","author":"Nazari"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICDMW53433.2021.00042"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053235"},{"key":"ref33","first-page":"1","article-title":"Combinatorial optimization by graph pointer networks and hierarchical reinforcement learning","volume-title":"Proc. AAAI","author":"Ma"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2020.1003231"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2005.1556401"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1287\/opre.51.6.850.24925"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511804441"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1126\/science.aar6404"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2020.2986641"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1515\/9781400822539"},{"volume-title":"Gurobi Optimizer Reference Manual","year":"2022","key":"ref41"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i1.16155"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9207026"},{"journal-title":"Artificial Intelligence and Games","year":"2018","author":"Yannakakis","key":"ref44"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2021.3078486"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-65530-7_3"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2022.3155533"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.3390\/a14110313"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.2307\/2951479"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/s001820050074"}],"container-title":["IEEE Transactions on Automation Science and Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/8856\/10839176\/10680425.pdf?arnumber=10680425","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,17]],"date-time":"2025-03-17T17:54:23Z","timestamp":1742234063000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10680425\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":50,"URL":"https:\/\/doi.org\/10.1109\/tase.2024.3456074","relation":{},"ISSN":["1545-5955","1558-3783"],"issn-type":[{"type":"print","value":"1545-5955"},{"type":"electronic","value":"1558-3783"}],"subject":[],"published":{"date-parts":[[2025]]}}}