Author:
Rahman M. H.,Bayrak A. E.,Sha Z.
Abstract
AbstractIn 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.
Publisher
Cambridge University Press (CUP)
Reference18 articles.
1. Drawing Inspiration From Human Design Teams for Better Search and Optimization: The Heterogeneous Simulated Annealing Teams Algorithm;McComb;Journal of Mechanical Design,2016
2. Learning an Optimization Algorithm Through Human Design Iterations;Sexton;Journal of Mechanical Design,2017
3. “Human and computational approaches for design problem-solving”, Experimental Design Research;Egan;Springer,2016
4. Impact of Heterogeneity and Risk Aversion on Task Allocation in Multi-Agent Teams;Wu;IEEE Robotics and Automation Letters,2021
5. Predicting Sequential Design Decisions Using the Function-Behavior-Structure Design Process Model and Recurrent Neural Networks;Rahman;Journal of Mechanical Design,2021