Construct, Merge, Solve & Adapt with Reinforcement Learning for the min-max Multiple Traveling Salesman Problem

Researchers developed RL-CMSA, a hybrid reinforcement learning approach for solving the min-max Multiple Traveling Salesman Problem that combines probabilistic clustering, exact optimization, and solution refinement. The method outperforms existing algorithms by balancing exploration and exploitation to minimize the longest tour across multiple salesmen.

• →RL-CMSA combines reinforcement learning with exact optimization techniques to solve complex routing optimization problems.
• →The hybrid approach uses probabilistic clustering guided by learned q-values to construct diverse solutions iteratively.
• →Computational results show consistent performance improvements over state-of-the-art genetic algorithms, especially for larger instances.
• →The method addresses workload balance by minimizing the longest tour in multi-salesman routing scenarios.
• →The approach demonstrates the effectiveness of combining machine learning with traditional optimization methods.