Benutzer: Gast  Login
Titel:

A Graph-Based Grammar for Structural Design using Deep Reinforcement Learning

Dokumenttyp:
Konferenzbeitrag
Art des Konferenzbeitrags:
Textbeitrag / Aufsatz
Autor(en):
Bleker, Lazlo; Tam, Kam-Ming Mark; D’Acunto, Pierluigi
Abstract:
This paper introduces a graph-based grammar method that combines the Combinatorial Equilibrium Modeling (CEM) form-finding approach and Deep Reinforcement Learning (RL). We formalize the design process of the CEM as a Markov Decision Process (MDP) that can act as an environment for an RL agent. This discrete step-wise design process allows both geometrical and topological manipulation of structural designs through a structural grammar consisting of a specific set of design actions. All design ac...     »
Stichworte:
structural grammar, form-finding, reinforcement learning, graph neural networks
Herausgeber:
International Association of Shell and Spatial Structures (IASS)
Kongress- / Buchtitel:
Proceedings of IASS 2024
Jahr:
2024
Sprache:
en
TUM Einrichtung:
Professorship of Structural Design
 BibTeX