Cooperative Solution to the Vehicle Routing Problem.

Cooperative multi-agent systems are rapidly growing subclass of the multi-agent systems where autonomous components allow to built and use several agent types acting in parallel while cooperatively solving a task. Possible form of such cooperation may be based, for example, on adaptive memory methods, where partial elements of good solutions are stored and next combined to create new complete solutions. Alternative possibility forms central memory approaches, where complete elite solutions are exchanged among various heuristics. Moreover, cooperatively solving a task is often combined with learning mechanism, where agents adapt their behavior to the new conditions of environment during the process of solving the problem. The goal of the paper is to propose a dedicated cooperative multi-agent system for solving the Vehicle Routing Problem with a reinforcement learning mechanism implemented in it. [ABSTRACT FROM AUTHOR]