- RIUMA Principal
- Listar por autor
Listar por autor "Ruiz-Montiel, Manuela"
Mostrando ítems 1-6 de 6
-
Aproximación Funcional en Aprendizaje por Refuerzo Multi-Objetivo
Ruiz-Montiel, Manuela (AEPIA, 2015)Describimos y comparamos dos t ecnicas para combinar m etodos de aproximaci on funcional y de escalarizaci on, con el objetivo de resolver problemas de aprendizaje por refuerzo con espacios de estados de tama~no elevado y ... -
Design with shapes grammars and reinforcement learning.
Ruiz-Montiel, Manuela; Boned-Purkiss, Francisco Javier; Gavilanes-Velaz-de-Medrano, Juan; Jiménez-Morales, Eduardo; Mandow-Andaluz, Lorenzo; Pérez-de-la-Cruz-Molina, José Luis[et al.] (Elsevier, 2013-01)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 ... -
Multi-objective Reinforcement Learning
Ruiz-Montiel, Manuela (2013-09-25)In this talk we present PQ-learning, a new Reinforcement Learning (RL) algorithm that determines the rational behaviours of an agent in multi-objective domains -
Proyecto Arquitectónico Energéticamente Eficiente Mediante Gramáticas de Formas y Aprendizaje por Refuerzo
Gavilanes-Velaz-de-Medrano, Juan; Hidalgo, Pablo; Belmonte, David; Mandow-Andaluz, Lorenzo; Ruiz-Montiel, Manuela (AEPIA, 2015)En este trabajo presentamos un sistema para la generación de esquemas de viviendas unifamiliares energéticamente eficientes. Los esquemas se sintetizan mediante la ejecución de gramáticas de formas simples, entrenadas por ... -
Randomness and control in design processes: an empirical study with architecture students.
Belmonte-Martínez, María Victoria; Millán-Valldeperas, Eva; Ruiz-Montiel, Manuela; Badillo, Reyes; Boned-Purkiss, Francisco Javier; Mandow-Andaluz, Lorenzo; Pérez-de-la-Cruz-Molina, José Luis[et al.] (2014-02-12)The aim of this study is to explore designers' preferences between randomness and control in the generation of architectural forms. To this end, a generative computer tool was implemented that allows both random and ... -
A temporal difference method for multi-objective reinforcement learning
This work describes MPQ-learning, an temporal-difference method that approximates the set of all non-dominated policies in multi-objective Markov decision problems, where rewards are vectors and each component stands for ...