Monte Carlo Tree Search as an intelligent search tool in structural design problems

Abstract Monte Carlo Tree Search (MCTS) is a search technique that in the last decade emerged as major breakthrough for Artificial Intelligence applications regarding board- and video-games. In 2016, AlphaGo, an MCTS-based software agent, outperformed human world champion of board game Go. This was long considered almost infeasible machines, due to its immense space need long-term strategy. Since this historical success, MCTS effective new approach many other scientific technical problems. Interestingly, civil structural engineering, discipline, offers tasks whose solution may benefit from intelligent particular adopting tool. work, we show how can be adapted suitable solutions engineering design problem. The problem consists choosing load-bearing elements reference reinforced concrete structure, so achieve set specific dynamic characteristics. paper, report results obtained by applying both plain hybrid version single-agent MCTS. integration classic Genetic Algorithm (GA), latter also serving term comparison results. study’s outcomes open perspectives adoption tool engineers.