{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T16:28:43Z","timestamp":1777652923603,"version":"3.51.4"},"reference-count":50,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2021,12,27]],"date-time":"2021-12-27T00:00:00Z","timestamp":1640563200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2021,12,27]],"date-time":"2021-12-27T00:00:00Z","timestamp":1640563200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci. China Inf. Sci."],"published-print":{"date-parts":[[2022,1]]},"DOI":"10.1007\/s11432-021-3348-6","type":"journal-article","created":{"date-parts":[[2022,1,5]],"date-time":"2022-01-05T06:02:24Z","timestamp":1641362544000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":95,"title":["Learning practically feasible policies for online 3D bin packing"],"prefix":"10.1007","volume":"65","author":[{"given":"Hang","family":"Zhao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chenyang","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hui","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kai","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,12,27]]},"reference":[{"key":"3348_CR1","doi-asserted-by":"publisher","first-page":"499","DOI":"10.1007\/978-3-642-25401-7_18","volume-title":"Kombinatorische Optimierung","author":"B Korte","year":"2012","unstructured":"Korte B, Vygen J. Bin-packing. In: Kombinatorische Optimierung. Berlin: Springer, 2012. 499\u2013516"},{"key":"3348_CR2","doi-asserted-by":"publisher","first-page":"256","DOI":"10.1287\/opre.48.2.256.12386","volume":"48","author":"S Martello","year":"2000","unstructured":"Martello S, Pisinger D, Vigo D. The three-dimensional bin packing problem. Oper Res, 2000, 48: 256\u2013267","journal-title":"Oper Res"},{"key":"3348_CR3","doi-asserted-by":"publisher","first-page":"368","DOI":"10.1287\/ijoc.1070.0250","volume":"20","author":"T G Crainic","year":"2008","unstructured":"Crainic T G, Perboli G, Tadei R. Extreme point-based heuristics for three-dimensional bin packing. Informs J Comput, 2008, 20: 368\u2013384","journal-title":"Informs J Comput"},{"key":"3348_CR4","doi-asserted-by":"crossref","unstructured":"Karabulut K, \u0130nceo\u011flu M M. A hybrid genetic algorithm for packing in 3D with deepest bottom left with fill method. In: Proceedings of International Conference on Advances in Information Systems, 2004. 441\u2013450","DOI":"10.1007\/978-3-540-30198-1_45"},{"key":"3348_CR5","doi-asserted-by":"crossref","unstructured":"Zhao H, She Q, Zhu C, et al. Online 3D bin packing with constrained deep reinforcement learning. In: Proceedings of the 35th AAAI Conference on Artificial Intelligence, the 33rd Conference on Innovative Applications of Artificial Intelligence, the 11th Symposium on Educational Advances in Artificial Intelligence, 2021. 741\u2013749","DOI":"10.1609\/aaai.v35i1.16155"},{"key":"3348_CR6","volume-title":"Constrained Markov Decision Processes","author":"E Altman","year":"1999","unstructured":"Altman E. Constrained Markov Decision Processes. Boca Raton: CRC Press, 1999"},{"key":"3348_CR7","unstructured":"Mnih V, Badia A P, Mirza M, et al. Asynchronous methods for deep reinforcement learning. In: Proceedings of International Conference on Machine Learning, 2016. 1928\u20131937"},{"key":"3348_CR8","unstructured":"Wu Y, Mansimov E, Grosse R B, et al. Scalable trust-region method for deep reinforcement learning using kronecker-factored approximation. In: Proceedings of Advances in Neural Information Processing Systems, 2017. 5279\u20135288"},{"key":"3348_CR9","doi-asserted-by":"publisher","first-page":"366","DOI":"10.1287\/mnsc.6.4.366","volume":"6","author":"L V Kantorovich","year":"1960","unstructured":"Kantorovich L V. Mathematical methods of organizing and planning production. Manage Sci, 1960, 6: 366\u2013422","journal-title":"Manage Sci"},{"key":"3348_CR10","doi-asserted-by":"crossref","unstructured":"Coffman E G, Garey M R, Johnson D S. Approximation algorithms for bin-packing\u2014an updated survey. In: Proceedings of Algorithm Design for Computer System Design, 1984. 49\u2013106","DOI":"10.1007\/978-3-7091-4338-4_3"},{"key":"3348_CR11","doi-asserted-by":"publisher","first-page":"267","DOI":"10.1287\/ijoc.15.3.267.16080","volume":"15","author":"O Faroe","year":"2003","unstructured":"Faroe O, Pisinger D, Zachariasen M. Guided local search for the three-dimensional bin-packing problem. Informs J Comput, 2003, 15: 267\u2013283","journal-title":"Informs J Comput"},{"key":"3348_CR12","doi-asserted-by":"publisher","first-page":"141","DOI":"10.1111\/1475-3995.00400","volume":"10","author":"S J L de Castro","year":"2003","unstructured":"de Castro S J L, Soma N Y, Maculan N. A greedy search for the three-dimensional bin packing problem: the packing static stability case. Int Trans Oper Res, 2003, 10: 141\u2013153","journal-title":"Int Trans Oper Res"},{"key":"3348_CR13","doi-asserted-by":"publisher","first-page":"158","DOI":"10.1016\/S0377-2217(97)00388-3","volume":"112","author":"A Lodi","year":"1999","unstructured":"Lodi A, Martello S, Vigo D. Approximation algorithms for the oriented two-dimensional bin packing problem. Eur J Oper Res, 1999, 112: 158\u2013166","journal-title":"Eur J Oper Res"},{"key":"3348_CR14","doi-asserted-by":"publisher","first-page":"744","DOI":"10.1016\/j.ejor.2007.06.063","volume":"195","author":"T G Crainic","year":"2009","unstructured":"Crainic T G, Perboli G, Tadei R. TS2PACK: a two-level tabu search for the three-dimensional bin packing problem. Eur J Oper Res, 2009, 195: 744\u2013760","journal-title":"Eur J Oper Res"},{"key":"3348_CR15","unstructured":"Li X, Zhao Z, Zhang K. A genetic algorithm for the three-dimensional bin packing problem with heterogeneous bins. In: Proceedings of Industrial and Systems Engineering Research Conference, 2014. 2039"},{"key":"3348_CR16","doi-asserted-by":"crossref","unstructured":"Takahara S, Miyamoto S. An evolutionary approach for the multiple container loading problem. In: Proceedings of the 5th International Conference on Hybrid Intelligent Systems, 2005. 227\u2013232","DOI":"10.1109\/ICHIS.2005.20"},{"key":"3348_CR17","doi-asserted-by":"crossref","unstructured":"Ha C T, Nguyen T T, Bui L T, et al. An online packing heuristic for the three-dimensional container loading problem in dynamic environments and the physical internet. In: Proceedings of European Conference on the Applications of Evolutionary Computation, 2017. 140\u2013155","DOI":"10.1007\/978-3-319-55792-2_10"},{"key":"3348_CR18","doi-asserted-by":"crossref","unstructured":"Wang R, Nguyen T T, Kavakeb S, et al. Benchmarking dynamic three-dimensional bin packing problems using discrete-event simulation. In: Proceedings of European Conference on the Applications of Evolutionary Computation, 2016. 266\u2013279","DOI":"10.1007\/978-3-319-31153-1_18"},{"key":"3348_CR19","doi-asserted-by":"publisher","first-page":"4448","DOI":"10.3390\/s20164448","volume":"20","author":"Y D Hong","year":"2020","unstructured":"Hong Y D, Kim Y J, Lee K B. Smart pack: online autonomous object-packing system using RGB-D sensor data. Sensors, 2020, 20: 4448","journal-title":"Sensors"},{"key":"3348_CR20","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1145\/1243980.1243986","volume":"26","author":"K Erleben","year":"2007","unstructured":"Erleben K. Velocity-based shock propagation for multibody dynamics animation. ACM Trans Graph, 2007, 26: 12","journal-title":"ACM Trans Graph"},{"key":"3348_CR21","unstructured":"Thomsen K K, Kraus M. Simulating small-scale object stacking using stack stability. In: Proceedings of the 23rd International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision WSCG 2015. Plzen: Vaclav Skala-UNION Agency, 2015. 5\u20138"},{"key":"3348_CR22","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2366145.2366169","volume":"31","author":"S W Hsu","year":"2012","unstructured":"Hsu S W, Keyser J. Automated constraint placement to maintain pile shape. ACM Trans Graph, 2012, 31: 1\u20136","journal-title":"ACM Trans Graph"},{"key":"3348_CR23","doi-asserted-by":"crossref","unstructured":"Han D, Hsu S W, McNamara A, et al. Believability in simplifications of large scale physically based simulation. In: Proceedings of the ACM Symposium on Applied Perception, 2013. 99\u2013106","DOI":"10.1145\/2492494.2492504"},{"key":"3348_CR24","unstructured":"Lillicrap T P, Hunt J J, Pritzel A, et al. Continuous control with deep reinforcement learning. 2015. ArXiv:1509.02971"},{"key":"3348_CR25","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih V, Kavukcuoglu K, Silver D, et al. Human-level control through deep reinforcement learning. Nature, 2015, 518: 529\u2013533","journal-title":"Nature"},{"key":"3348_CR26","unstructured":"Wang Z, Schaul T, Hessel M, et al. Dueling network architectures for deep reinforcement learning. 2015. ArXiv:1511.06581"},{"key":"3348_CR27","unstructured":"Silver D, Lever G, Heess N, et al. Deterministic policy gradient algorithms. In: Proceedings of the 31st International Conference on International Conference on Machine Learning, 2014. 387\u2013395"},{"key":"3348_CR28","unstructured":"Barth-Maron G, Hoffman M W, Budden D, et al. Distributed distributional deterministic policy gradients. 2018. ArXiv:1804.08617"},{"key":"3348_CR29","unstructured":"Schulman J, Wolski F, Dhariwal P, et al. Proximal policy optimization algorithms. 2017. ArXiv:1707.06347"},{"key":"3348_CR30","unstructured":"Bello I, Pham H, Le Q V, et al. Neural combinatorial optimization with reinforcement learning. 2016. ArXiv:1611.09940"},{"key":"3348_CR31","unstructured":"Kool W, van Hoof H, Welling M. Attention, learn to solve routing problems! In: Proceedings of the 7th International Conference on Learning Representations, 2019"},{"key":"3348_CR32","unstructured":"Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need. In: Proceedings of Annual Conference on Neural Information Processing Systems, Long Beach, 2017. 5998\u20136008"},{"key":"3348_CR33","unstructured":"Zhang C, Song W, Cao Z, et al. Learning to dispatch for job shop scheduling via deep reinforcement learning. In: Proceedings of Annual Conference on Neural Information Processing Systems, 2020"},{"key":"3348_CR34","first-page":"1","volume":"39","author":"H Wang","year":"2020","unstructured":"Wang H, Liang W, Yu L F. Scene mover: automatic move planning for scene arrangement by deep reinforcement learning. ACM Trans Graph, 2020, 39: 1\u201315","journal-title":"ACM Trans Graph"},{"key":"3348_CR35","unstructured":"Hu H, Zhang X, Yan X, et al. Solving a new 3D bin packing problem with deep reinforcement learning method. 2017. ArXiv:1708.05930"},{"key":"3348_CR36","unstructured":"Laterre A, Fu Y, Jabri M K, et al. Ranked reward: enabling self-play reinforcement learning for combinatorial optimization. 2018. ArXiv:1807.01672"},{"key":"3348_CR37","doi-asserted-by":"crossref","unstructured":"Uchibe E, Doya K. Constrained reinforcement learning from intrinsic and extrinsic rewards. In: Proceedings of the 6th International Conference on Development and Learning, 2007. 163\u2013168","DOI":"10.1109\/DEVLRN.2007.4354030"},{"key":"3348_CR38","first-page":"6070","volume":"18","author":"Y Chow","year":"2017","unstructured":"Chow Y, Ghavamzadeh M, Janson L, et al. Risk-constrained reinforcement learning with percentile risk criteria. J Mach Learn Res, 2017, 18: 6070\u20136120","journal-title":"J Mach Learn Res"},{"key":"3348_CR39","unstructured":"Achiam J, Held D, Tamar A, et al. Constrained policy optimization. In: Proceedings of the 34th International Conference on Machine Learning-Volume 70, 2017. 22\u201331"},{"key":"3348_CR40","unstructured":"Martens J, Grosse R. Optimizing neural networks with Kronecker-factored approximate curvature. In: Proceedings of International Conference on Machine Learning, 2015. 2408\u20132417"},{"key":"3348_CR41","unstructured":"Haarnoja T, Zhou A, Abbeel P, et al. Soft actor-critic: off-policy maximum entropy deep reinforcement learning with a stochastic actor. 2018. ArXiv:1801.01290"},{"key":"3348_CR42","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1145\/1206040.1206047","volume":"33","author":"S Martello","year":"2007","unstructured":"Martello S, Pisinger D, Vigo D, et al. Algorithm 864: general and robot-packable variants of the three-dimensional bin packing problem. ACM Trans Math Softw, 2007, 33: 7","journal-title":"ACM Trans Math Softw"},{"key":"3348_CR43","doi-asserted-by":"crossref","unstructured":"Tavakoli A, Pardo F, Kormushev P. Action branching architectures for deep reinforcement learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, 2018","DOI":"10.1609\/aaai.v32i1.11798"},{"key":"3348_CR44","doi-asserted-by":"publisher","first-page":"354","DOI":"10.1038\/nature24270","volume":"550","author":"D Silver","year":"2017","unstructured":"Silver D, Schrittwieser J, Simonyan K, et al. Mastering the game of Go without human knowledge. Nature, 2017, 550: 354\u2013359","journal-title":"Nature"},{"key":"3348_CR45","doi-asserted-by":"crossref","unstructured":"Chaslot G M B, Winands M H, van den Herik H J. Parallel Monte-Carlo tree search. In: Proceedings of International Conference on Computers and Games, 2008. 60\u201371","DOI":"10.1007\/978-3-540-87608-3_6"},{"key":"3348_CR46","doi-asserted-by":"crossref","unstructured":"Dekel A, Harenstam-Nielsen L, Caccamo S. Optimal least-squares solution to the hand-eye calibration problem. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020. 13598\u201313606","DOI":"10.1109\/CVPR42600.2020.01361"},{"key":"3348_CR47","doi-asserted-by":"crossref","unstructured":"Feng C, Taguchi Y, Kamat V R. Fast plane extraction in organized point clouds using agglomerative hierarchical clustering. In: Proceedings of IEEE International Conference on Robotics and Automation (ICRA), 2014. 6218\u20136225","DOI":"10.1109\/ICRA.2014.6907776"},{"key":"3348_CR48","unstructured":"Paszke A, Gross S, Massa F, et al. PyTorch: an imperative style, high-performance deep learning library. In: Proceedings of Advances in Neural Information Processing Systems, 2019. 8024\u20138035"},{"key":"3348_CR49","doi-asserted-by":"publisher","first-page":"849","DOI":"10.1287\/opre.9.6.849","volume":"9","author":"P C Gilmore","year":"1961","unstructured":"Gilmore P C, Gomory R E. A linear programming approach to the cutting-stock problem. Oper Res, 1961, 9: 849\u2013859","journal-title":"Oper Res"},{"key":"3348_CR50","doi-asserted-by":"crossref","unstructured":"Coumans E. Bullet physics simulation. In: Proceedings of ACM SIGGRAPH 2015 Courses, 2015","DOI":"10.1145\/2776880.2792704"}],"container-title":["Science China Information Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11432-021-3348-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11432-021-3348-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11432-021-3348-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,3]],"date-time":"2023-02-03T21:22:01Z","timestamp":1675459321000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11432-021-3348-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,27]]},"references-count":50,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2022,1]]}},"alternative-id":["3348"],"URL":"https:\/\/doi.org\/10.1007\/s11432-021-3348-6","relation":{},"ISSN":["1674-733X","1869-1919"],"issn-type":[{"value":"1674-733X","type":"print"},{"value":"1869-1919","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,12,27]]},"assertion":[{"value":"8 July 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 August 2021","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 September 2021","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 December 2021","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"112105"}}