Optimizing Retaining Walls through Reinforcement Learning Approaches and Metaheuristic Techniques

The structural design of civil works is closely tied to empirical knowledge and the professional’s experience. Based on this, adequate designs are generated in terms strength, operability, durability. However, such can be optimized reduce conditions associated with structure’s execution, as costs, CO2 emissions, related earthworks. In this study, a new discretization technique based reinforcement learning transfer functions developed. application metaheuristic techniques retaining wall problem examined, defining two objective functions: cost emissions. An extensive comparison made various metaheuristics brute force methods, where results show that S-shaped consistently yield more robust outcomes.