An approach to solving combinatorial optimization problems using a population of reinforcement learning agents

This paper presents an approach that uses reinforcement learning (RL) algorithms to solve combinatorial optimization problems. In particular, the approach combines both local and global search characteristics: local information as encoded by typical RL schemes and global information as contained in a population of search agents. The effectiveness of the approach is demonstrated on both the Asymmetric Traveling Salesman (ATSP) and the Quadratic Assignment Problem (QAP). These results are competitive with other well-known search techniques and suggest that the presented RL-agent approach can be used as a basis for global optimization techniques.