{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T01:00:18Z","timestamp":1770339618634,"version":"3.49.0"},"reference-count":60,"publisher":"Cambridge University Press (CUP)","license":[{"start":{"date-parts":[[2023,6,13]],"date-time":"2023-06-13T00:00:00Z","timestamp":1686614400000},"content-version":"unspecified","delay-in-days":163,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["cambridge.org"],"crossmark-restriction":true},"short-container-title":["AIEDAM"],"published-print":{"date-parts":[[2023]]},"abstract":"<jats:title>Abstract<\/jats:title>\n\t  <jats:p>The use of local natural and recycled feedstock is promising for sustainable construction. However, unlike versatile engineered bricks, natural and recycled feedstock involves design challenges due to their stochastic, sequential, and heterogeneous nature. For example, the practical use of stone masonry is limited, as it still relies on human experts with holistic domain knowledge to determine the sequential organization of natural stones with different sizes\/shapes. Reinforcement learning (RL) is expected to address such design challenges, as it allows artificial intelligence (AI) agents to autonomously learn design policy, that is, identifying the best design decision at each time step. As a proof-of-concept RL framework for design automation involving heterogeneous feedstock, a stone masonry design framework is presented. The proposed framework is founded upon a virtual design environment, <jats:italic>MasonTris<\/jats:italic>, inspired by the analogy between stone masonry and Tetris. <jats:italic>MasonTris<\/jats:italic> provides a Tetris-like virtual environment combined with a finite element analysis (FEA), where AI agents learn effective design policies without human intervention. Also, a new data collection policy, <jats:italic>almost-greedy policy<\/jats:italic>, is designed to address the sparsity of feasible designs for faster\/stable learning. As computation bottleneck occurs when parallel agents evaluate designs with different complexities, a modification of the RL framework is proposed that FEA is held until training data are retrieved for training. The feasibility and adaptability of the proposed framework are demonstrated by continuously improving stone masonry design policy in simplified design problems. The framework can be generalizable to different natural and recycled feedstock by incorporating more realistic assumptions, opening opportunities in design automation for sustainability.<\/jats:p>","DOI":"10.1017\/s0890060423000100","type":"journal-article","created":{"date-parts":[[2023,6,13]],"date-time":"2023-06-13T12:35:04Z","timestamp":1686659704000},"update-policy":"https:\/\/doi.org\/10.1017\/policypage","source":"Crossref","is-referenced-by-count":4,"title":["Stone masonry design automation via reinforcement learning"],"prefix":"10.1017","volume":"37","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8146-4103","authenticated-orcid":false,"given":"SungKu","family":"Kang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jennifer G.","family":"Dy","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael B.","family":"Kane","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"56","published-online":{"date-parts":[[2023,6,13]]},"reference":[{"key":"S0890060423000100_ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s00158-017-1837-7"},{"key":"S0890060423000100_ref6","unstructured":"ANSYS Granta (2019) Material property chart created using CES EduPack 2019. Available at shorturl.at\/crwQ5."},{"key":"S0890060423000100_ref41","doi-asserted-by":"publisher","DOI":"10.1007\/s00158-013-0978-6"},{"key":"S0890060423000100_ref52","first-page":"458","article-title":"SSIEA: a hybrid evolutionary algorithm for supporting conceptual architectural design","volume":"34","author":"Wang","year":"2020","journal-title":"AI EDAM"},{"key":"S0890060423000100_ref25","doi-asserted-by":"publisher","DOI":"10.1115\/1.4044397"},{"key":"S0890060423000100_ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.autcon.2019.103062"},{"key":"S0890060423000100_ref42","volume-title":"Robots Lay Three Times as Many Bricks as Construction Workers","author":"Sklar","year":"2015"},{"key":"S0890060423000100_ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TSC.2018.2867482"},{"key":"S0890060423000100_ref23","doi-asserted-by":"publisher","DOI":"10.1115\/1.4035420"},{"key":"S0890060423000100_ref38","doi-asserted-by":"publisher","DOI":"10.25080\/Majora-7b98e3ed-013"},{"key":"S0890060423000100_ref3","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1905.01652"},{"key":"S0890060423000100_ref36","first-page":"180","article-title":"A self-learning finite element extraction system based on reinforcement learning","volume":"35","author":"Pan","year":"2021","journal-title":"AI EDAM"},{"key":"S0890060423000100_ref54","first-page":"471","article-title":"Advantages of surrogate models for architectural design optimization","volume":"29","author":"Wortmann","year":"2015","journal-title":"AI EDAM"},{"key":"S0890060423000100_ref49","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"S0890060423000100_ref53","doi-asserted-by":"publisher","DOI":"10.1145\/2366145.2366178"},{"key":"S0890060423000100_ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s11831-019-09351-x"},{"key":"S0890060423000100_ref37","doi-asserted-by":"publisher","DOI":"10.1126\/sciadv.aap7885"},{"key":"S0890060423000100_ref15","unstructured":"Glorot, X and Bengio, Y (2010) Understanding the difficulty of training deep feedforward neural networks. Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, 249\u2013256. JMLR Workshop and Conference Proceedings. Available at https:\/\/proceedings.mlr.press\/v9\/glorot10a.html."},{"key":"S0890060423000100_ref27","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992699"},{"key":"S0890060423000100_ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.cad.2016.09.009"},{"key":"S0890060423000100_ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.autcon.2021.103826"},{"key":"S0890060423000100_ref14","doi-asserted-by":"publisher","DOI":"10.17831\/rep:arcc"},{"key":"S0890060423000100_ref2","first-page":"393","article-title":"Evolutionary structural and spatial adaptation of topologically differentiated tensile systems in architectural design","volume":"29","author":"Ahlquist","year":"2015","journal-title":"AI EDAM"},{"key":"S0890060423000100_ref21","first-page":"351","article-title":"Coevolutionary and genetic algorithm based building spatial and structural design","volume":"29","author":"Hofmeyer","year":"2015","journal-title":"AI EDAM"},{"key":"S0890060423000100_ref30","first-page":"147","article-title":"Design characteristics and aesthetics in evolutionary design of architectural forms directed by fuzzy evaluation","volume":"34","author":"Mars","year":"2020","journal-title":"AI EDAM"},{"key":"S0890060423000100_ref8","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"S0890060423000100_ref58","doi-asserted-by":"publisher","DOI":"10.1016\/j.autcon.2020.103346"},{"key":"S0890060423000100_ref48","doi-asserted-by":"publisher","DOI":"10.1016\/S0378-7788(01)00141-4"},{"key":"S0890060423000100_ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.autcon.2018.06.015"},{"key":"S0890060423000100_ref59","doi-asserted-by":"publisher","DOI":"10.1016\/j.softx.2017.10.009"},{"key":"S0890060423000100_ref55","doi-asserted-by":"publisher","DOI":"10.1016\/j.aei.2022.101621"},{"key":"S0890060423000100_ref34","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1912.06680"},{"key":"S0890060423000100_ref43","first-page":"457","article-title":"A fast genetic algorithm for solving architectural design optimization problems","volume":"29","author":"Su","year":"2015","journal-title":"AI EDAM"},{"key":"S0890060423000100_ref60","doi-asserted-by":"publisher","DOI":"10.1007\/s00158-016-1513-3"},{"key":"S0890060423000100_ref18","article-title":"Deep reinforcement learning with double Q-learning","volume":"30","author":"Hasselt","year":"2016","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"S0890060423000100_ref20","volume-title":"Energy Manual: sustainable Architecture","author":"Hegger","year":"2012"},{"key":"S0890060423000100_ref39","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3987"},{"key":"S0890060423000100_ref22","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1115898108"},{"key":"S0890060423000100_ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.autcon.2021.103858"},{"key":"S0890060423000100_ref47","volume-title":"Transfer Learning","author":"Torrey","year":"2010"},{"key":"S0890060423000100_ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s00158-013-1018-2"},{"key":"S0890060423000100_ref31","unstructured":"Masonry Standards Joint Committee. (2002) ACI 530-02\/ASCE 5-02\/TMS 402-02. Building code requirements for Masonry structures."},{"key":"S0890060423000100_ref56","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2018.8500630"},{"key":"S0890060423000100_ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s00366-019-00926-7"},{"key":"S0890060423000100_ref1","unstructured":"Abadi, M , Agarwal, A , Barham, P , Brevdo, E , Chen, Z , Citro, C , Corrado, GS , Davis, A , Dean, J , Devin, M , Ghemawat, S , Goodfellow, I , Harp, A , Irving, G , Isard, M , Jozefowicz, R , Jia, Y , Kaiser, L , Kudlur, M , Levenberg, J , Man\u00e9, D , Schuster, M , Monga, R , Moore, S , Murray, D , Olah, C , Shlens, J , Steiner, B , Sutskever, I , Talwar, K , Tucker, P , Vanhoucke, V , Vasudevan, V , Vi\u00e9gas, F , Vinyals, O , Warden, P , Wattenberg, M , Wicke, M , Yu, Y and Zheng, X (2015) TensorFlow: large-scale machine learning on heterogeneous systems. Available at https:\/\/www.tensorflow.org\/."},{"key":"S0890060423000100_ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s00158-020-02748-4"},{"key":"S0890060423000100_ref35","doi-asserted-by":"publisher","DOI":"10.1061\/(ASCE)CF.1943-5509.0001057"},{"key":"S0890060423000100_ref26","article-title":"Machine learning-driven real-time topology optimization under moving morphable component-based framework","volume":"86","author":"Lei","year":"2018","journal-title":"Journal of Applied Mechanics"},{"key":"S0890060423000100_ref32","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1312.5602"},{"key":"S0890060423000100_ref46","doi-asserted-by":"publisher","DOI":"10.1016\/j.conbuildmat.2012.07.095"},{"key":"S0890060423000100_ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.autcon.2020.103156"},{"key":"S0890060423000100_ref24","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"S0890060423000100_ref13","doi-asserted-by":"publisher","DOI":"10.1090\/qam\/48291"},{"key":"S0890060423000100_ref51","doi-asserted-by":"publisher","DOI":"10.1016\/j.cma.2003.10.008"},{"key":"S0890060423000100_ref33","doi-asserted-by":"publisher","DOI":"10.1051\/matecconf\/201814901077"},{"key":"S0890060423000100_ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.conbuildmat.2019.05.192"},{"key":"S0890060423000100_ref45","volume-title":"Introduction to Reinforcement Learning","volume":"135","author":"Sutton","year":"1998"},{"key":"S0890060423000100_ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s00158-018-2089-x"},{"key":"S0890060423000100_ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s11465-013-0248-8"},{"key":"S0890060423000100_ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.jobe.2020.101816"}],"container-title":["Artificial Intelligence for Engineering Design, Analysis and Manufacturing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.cambridge.org\/core\/services\/aop-cambridge-core\/content\/view\/S0890060423000100","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,26]],"date-time":"2023-07-26T06:18:28Z","timestamp":1690352308000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.cambridge.org\/core\/product\/identifier\/S0890060423000100\/type\/journal_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":60,"alternative-id":["S0890060423000100"],"URL":"https:\/\/doi.org\/10.1017\/s0890060423000100","relation":{},"ISSN":["0890-0604","1469-1760"],"issn-type":[{"value":"0890-0604","type":"print"},{"value":"1469-1760","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"Copyright \u00a9 The Author(s), 2023. Published by Cambridge University Press","name":"copyright","label":"Copyright","group":{"name":"copyright_and_licensing","label":"Copyright and Licensing"}},{"value":"This is an Open Access article, distributed under the terms of the Creative Commons Attribution-ShareAlike licence (http:\/\/creativecommons.org\/licenses\/by-sa\/4.0), which permits re-use, distribution, and reproduction in any medium, provided the same Creative Commons licence is used to distribute the re-used or adapted article and the original article is properly cited.","name":"license","label":"License","group":{"name":"copyright_and_licensing","label":"Copyright and Licensing"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}],"article-number":"e17"}}