arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2207.04857cs.NEcs.AIcs.LG
收藏

进化算法中的新事物

Emergence of Novelty in Evolutionary Algorithms

Czech Institute of Informatics, Robotics and Cybernetics, Czech Technical University in Prague(布拉格捷克理工大学捷克信息学、机器人与控制论研究所);Faculty of Electrical Engineering, Czech Technical University in Prague(布拉格捷克理工大学电气工程学院);Charles University in Prague(布拉格查理大学);GoodAI Research(GoodAI研究院)

David Herel, Dominika Zogatova, Matej Kripner, Tomas Mikolov

摘要:

进化算法的主要问题之一是种群收敛到局部极小点。在本文中,我们探讨的技术,可以避免这个问题,通过鼓励不同的行为的代理人通过共享奖励系统。奖励在环境中随机分布,代理人只会因为首先收集它们而获得奖励。这导致了代理人的新行为的出现。我们介绍了我们的迷宫问题的方法,并将其与先前提出的解决方案进行比较,称为新奇搜索(Lehman和Stanley,2011 a)。我们发现,我们的解决方案可以提高性能,同时显着更简单。在此基础上,我们概括了这个问题,并将我们的方法应用于一组更高级的任务,雅达利游戏,在那里我们观察到类似的性能质量,需要更少的计算能力。

英文摘要:

One of the main problems of evolutionary algorithms is the convergence of the population to local minima. In this paper, we explore techniques that can avoid this problem by encouraging a diverse behavior of the agents through a shared reward system. The rewards are randomly distributed in the environment, and the agents are only rewarded for collecting them first. This leads to an emergence of a novel behavior of the agents. We introduce our approach to the maze problem and compare it to the previously proposed solution, denoted as Novelty Search (Lehman and Stanley, 2011a). We find that our solution leads to an improved performance while being significantly simpler. Building on that, we generalize the problem and apply our approach to a more advanced set of tasks, Atari Games, where we observe a similar performance quality with much less computational power needed.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑