SSGTA: A Novel Swap Sequence based Game Theory Algorithm for Traveling Salesman Problem

Abstract

Many approaches have been developed to make intelligent moves imitating rational decision-makers. Game theory provides a theoretical framework that can be efficiently employed in solving complex optimization problems. The area of applied mathematics that investigates the strategic behavior of rational factors is known as game theory. In other terms, game theory is an analytical tool for making the optimal decision in interaction and decision-making situations. The Traveling Salesman Problem (TSP) is solved using this research’s swap sequence-based game theory algorithm (SSGTA). TSP is a well-known combinatorial optimization real problem. TSP is also widely used to assess expertise in newly emerging optimization techniques. Furthermore, optimization techniques established for other tasks (such as numerical optimization) are tested for TSP competency. A player attempts to update its solution using another player. An expected payoff mechanism is proposed to choose the learning strategy. Based on the improvement of solution quality, a payoff is awarded to the winning player. When no improvement is noticed in the solution, the 2-opt algorithm is employed to get over the local optimal. SSGTA is tested for several benchmark TSP instances from TSPLIB and compared with some other recent methods. SSGTA performs better than different algorithms on accuracy and stability.