Publications
Detailed Information
Task-Oriented Design through Deep Reinforcement Learning
Cited 0 time in
Web of Science
Cited 0 time in Scopus
- Authors
- Advisor
- 곽노준
- Major
- 융합과학기술대학원 지능형융합시스템학과
- Issue Date
- 2019-02
- Publisher
- 서울대학교 대학원
- Description
- 학위논문 (석사)-- 서울대학교 대학원 : 융합과학기술대학원 지능형융합시스템학과, 2019. 2. 곽노준.
- Abstract
- We propose a new low-cost machine-learning-based methodology which
assists designers in reducing the gap between the problem and the solution
in the design process. Our work applies reinforcement learning (RL) to find
the optimal task-oriented design solution through the construction of the
design action for each task. For this task-oriented design, the 3D design
process in product design is assigned to an action space in Deep RL, and a
desired 3D model is obtained by training each design action according to the
task. By showing that this method achieves satisfactory design even when
applied to a task pursuing multiple goals, we suggest the direction of how
machine learning can contribute in design process. Also, we have validated
with product designers that this methodology can assist the creative part in
the process of design.
- Language
- eng
- Files in This Item:
Item View & Download Count
Items in S-Space are protected by copyright, with all rights reserved, unless otherwise indicated.