User: Guest  Login
Title:

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

Document type:
Konferenzbeitrag
Contribution type:
Textbeitrag / Aufsatz
Author(s):
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...     »
Keywords:
structural grammar, form-finding, reinforcement learning, graph neural networks
Editor:
International Association of Shell and Spatial Structures (IASS)
Book / Congress title:
Proceedings of IASS 2024
Year:
2024
Language:
en
TUM Institution:
Professorship of Structural Design
 BibTeX