This work highlights the solution to the problem of finding the minimum size of an enterprise’s vehicle fleet, with which it is possible to solve problems similar to the problem of several traveling salesmen. The proposed approach models a reinforcement learning environment where an agent must drive around given waypoints with multiple vehicles. The conducted computational experiments showed the effectiveness of machine learning models in solving the combinatorial optimization problem.

reinforcement learning, combinatorial optimization, traveling salesman problem, car fleet

Mathematical modelling in actual problems of science and technics

Shmyglev Dmitry Nikolaevich,  lev.shmyg@gmail.com,  orcid.org/0009-0007-5513-8903,  Financial University under the Government of the RF

Sudakov Vladimir Anatolievich,  sudakov@ws-dss.com,  orcid.org/0000-0002-1658-1941,  KIAM RAS; Financial University under the Government of the RF