Reinforcement machine learning for solving mathematical programming problems

This paper discusses modern approaches to finding rational solutions in problems of mixed integer linear programming, both generated with random data and from real practice. The main emphasis is on how to implement the process of finding a solution to discrete optimization problems using the concept of reinforcement learning; what techniques can be applied to improve the speed and quality of work. Three main variants of the algorithm were developed using the Ray library API, as well as the environment - the Gym library. The results of the developed solver are compared with the OR-Tools library. The best model can be used as a solver for high-dimensional optimization problems, in addition, this concept is applicable to other combinatorial problems with a change in the environment code and the intelligent agent algorithm.