Learning Proficient Behavior With Computational Agents in Engineering Configuration Design
Journal of Mechanical Design · 01.02.2025 · 147 (2)
DOI: 10.1115/1.4066126 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Mechanical Design, online erschienen am 28.08.2024. Verfasst von Ethan Brownell und 2 weiteren Autor:innen. Die Arbeit nennt 45 Literaturangaben. Gefördert von: Air Force Office of Scientific Research.
Abstract (Originalsprache)
A novel approach for computational agents to learn proficient behavior in engineering configuration design that is inspired by human learning is introduced in this work. The learning proficient simulated annealing design agents (LPSADA) begin as different proficiency designers and are explicitly modeled to mimic the design behavior and performance of different proficiency human designers. A learning methodology, which is inspired by human learning, is introduced to update the characteristics of the agents that dictate their behavior. The methods are designed to change their behavioral characteristics based on their experience, including a non-deterministic reinforcement learning algorithm. Results show that the lower-proficiency agents successfully change their behavior to act more like high-proficiency designers. These behavior changes are shown to increase the performance of the lower-proficiency agents to the levels of high-proficiency human designers. In sum, the learning methodology that is introduced is shown to allow lower-proficiency agents to become higher-proficiency designers.
Förderung
- Air Force Office of Scientific Research
Zitieren
APA
Brownell, E., Kotovsky, K., & Cagan, J. (2025). Learning Proficient Behavior With Computational Agents in Engineering Configuration Design. Journal of Mechanical Design, 147(2). https://doi.org/10.1115/1.4066126
Vancouver
Brownell E, Kotovsky K, Cagan J. Learning Proficient Behavior With Computational Agents in Engineering Configuration Design. Journal of Mechanical Design. 2025;147(2). doi:10.1115/1.4066126
BibTeX
@article{Brownell2025,
author = {Brownell, Ethan and Kotovsky, Kenneth and Cagan, Jonathan},
title = {Learning Proficient Behavior With Computational Agents in Engineering Configuration Design},
journal = {Journal of Mechanical Design},
year = {2025},
volume = {147},
number = {2},
doi = {10.1115/1.4066126}
}
EUVIMED