Evolutionary multi-agent systems

In Multi-Agent learning, agents must learn to select actions that maximize their utility given the action choices of the other agents. Cooperative Coevolution offers a way to evolve multiple elements that together form a whole, by using a separate population for each element. We apply this setup to the problem of multi-agent learning, arriving at an evolutionary multi-agent system (EA-MAS). We study a problem that requires agents to select their actions in parallel, and investigate the problem solving capacity of the EA-MAS for a wide range of settings. Secondly, we investigate the transfer of the COllective INtelligence (COIN) framework to the EA-MAS. COIN is a proved engineering approach for learning of cooperative tasks in MASs, and consists of re-engineering the utilities of the agents so as to contribute to the global utility. It is found that, as in the Reinforcement Learning case, the use of the Wonderful Life Utility specified by COIN also leads to improved results for the EA-MAS.