Optimal Cislunar Architecture Design Using Monte Carlo Tree Search Methods
A novel multi-objective Monte Carlo Tree Search (MO-MCTS) algorithm is developed and implemented for use in architecture design problems. This algorithm is implemented on two well-known problems with known solutions to verify its performance. It is then used in a highly nonlinear cislunar architecture design problem with no known analytical solutions. The results of this implementation display the ability of MO-MCTS to effectively navigate the state space of mixed integer nonlinear programming problems and emphasize the versatility of MO-MCTS for designing critical cislunar architecture.