TY - JOUR
T1 - A Reinforcement Learning Approach to Predicting Human Design Actions Using a Data-Driven Reward Formulation
AU - Rahman, M. H.
AU - Bayrak, A. E.
AU - Sha, Z.
N1 - Publisher Copyright:
© The Author(s), 2022.
PY - 2022/5
Y1 - 2022/5
N2 - In this paper, we develop a design agent based on reinforcement learning to mimic human design behaviours. A data-driven reward mechanism based on the Markov chain model is introduced so that it can reinforce prominent and beneficial design patterns. The method is implemented on a set of data collected from a solar system design problem. The result indicates that the agent provides higher prediction accuracy than the baseline Markov chain model. Several design strategies are also identified that differentiate high-performing designers from low-performing designers.
AB - In this paper, we develop a design agent based on reinforcement learning to mimic human design behaviours. A data-driven reward mechanism based on the Markov chain model is introduced so that it can reinforce prominent and beneficial design patterns. The method is implemented on a set of data collected from a solar system design problem. The result indicates that the agent provides higher prediction accuracy than the baseline Markov chain model. Several design strategies are also identified that differentiate high-performing designers from low-performing designers.
KW - artificial intelligence (AI)
KW - design thinking
KW - human behaviour
UR - http://www.scopus.com/inward/record.url?scp=85131380554&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85131380554&partnerID=8YFLogxK
U2 - 10.1017/pds.2022.173
DO - 10.1017/pds.2022.173
M3 - Conference article
AN - SCOPUS:85131380554
VL - 2
SP - 1709
EP - 1718
JO - Proceedings of the Design Society
JF - Proceedings of the Design Society
T2 - 17th International Design Conference, DESIGN 2022
Y2 - 23 May 2022 through 26 May 2022
ER -