RT Journal Article
T1 Design with shapes grammars and reinforcement learning.
A1 Ruiz-Montiel, Manuela
A1 Boned-Purkiss, Francisco Javier
A1 Gavilanes-Velaz-de-Medrano, Juan
A1 Jiménez-Morales, Eduardo
A1 Mandow-Andaluz, Lorenzo
A1 Pérez-de-la-Cruz-Molina, José Luis
K1 Diseño asistido por ordenador
K1 Arquitectura - Estudio y enseñanza superior - Innovaciones tecnológicas
AB Shape grammars are a powerful and appealing formalism for automatic shape generation in computer-based design systems. This paper presents a proposal complementing the generative power of shape grammars with reinforcement learning techniques. We use simple (naive) shape grammars capable of generating a large variety of different designs. In order to generate those designs that comply with given design requirements, the grammar is subject to a process of machine learning using reinforcement learning techniques. Based on this method, we have developed a system for architectural design, aimed at generating two-dimensional layout schemes of single-family housing units. Using relatively simple grammar rules, we learn to generate schemes that satisfy a set of requirements stated in a design guideline. Obtained results are presented and discussed.
PB Elsevier
YR 2013
FD 2013-01
LK https://hdl.handle.net/10630/29339
UL https://hdl.handle.net/10630/29339
LA eng
NO Manuela Ruiz-Montiel, Javier Boned, Juan Gavilanes, Eduardo Jiménez, Lawrence Mandow, José-Luis Pérez-de-la-Cruz, Design with shape grammars and reinforcement learning, Advanced Engineering Informatics, Volume 27, Issue 2, 2013, Pages 230-245, ISSN 1474-0346, https://doi.org/10.1016/j.aei.2012.12.004.
NO Política de acceso abierto tomada de: https://v2.sherpa.ac.uk/id/publication/1733
NO La publicación recoge los resultados del proyecto “Nuevas Técnicas Inteligentes de Decisión Aplicada al Proyecto Arquitectónico” (TIN2009-14179, Gobierno de España)
DS RIUMA. Repositorio Institucional de la Universidad de Málaga
RD 21 ene 2026