Explore the application of reinforced learning to support decision making during the design phase in the construction industry

As indicated by several researchers, the objective assessment of design prior to commencing construction is essential for achieving sustainability requirements and improving the competitiveness of the construction company. This process is far from being a simple task, as it requires a detailed evaluation of a plethora of options that designers may not have time to do. To help designers evaluating the excessive number of possible design combinations they encounter, this paper explores the application of reinforced learning (RL) to develop a model that assist designers in their pursuit of the optimal design. The present research utilizes the Markov Decision Process (MDP) as an application of RL and multi-attribute utility to solve the problem of the objective assessment of the design. The paper also presents a case study that demonstrates the utilization of the developed model to optimize the design of a single-family house.