平衡选择压力、多目标和神经模块以共同进化合作Agent行为
Balancing Selection Pressures, Multiple Objectives, and Neural Modularity to Coevolve Cooperative Agent Behavior
摘要：
以往的研究表明，在多智能体系统中使用演化计算，基于团队与个人行为对人工智能体的进化团队在具有挑战性的任务中表现出团队合作的能力有很大的影响。然而，这种研究只使用了单目标进化。相比之下，当使用多目标进化算法时，种群可以服从个人级目标、团队级目标或两者的组合。本文探讨了人工神经网络受这些类型的目标控制的代理合作共同进化团队的性能。具体来说，捕食者代理被进化为在环形网格世界中捕获脚本猎物代理。由于个体和团队行为之间的张力，多种行为模式可能是有用的，因此模块化神经网络的效果也进行了探讨。结果表明，健身奖励个人行为优于健身奖励团队行为，尽管被应用到一个合作的任务。然而，使用具有多个模块的网络允许捕食者发现智能行为，无论使用哪种类型的目标。
英文摘要：
Previous research using evolutionary computation in Multi-Agent Systems indicates that assigning fitness based on team vs.\ individual behavior has a strong impact on the ability of evolved teams of artificial agents to exhibit teamwork in challenging tasks. However, such research only made use of single-objective evolution. In contrast, when a multiobjective evolutionary algorithm is used, populations can be subject to individual-level objectives, team-level objectives, or combinations of the two. This paper explores the performance of cooperatively coevolved teams of agents controlled by artificial neural networks subject to these types of objectives. Specifically, predator agents are evolved to capture scripted prey agents in a torus-shaped grid world. Because of the tension between individual and team behaviors, multiple modes of behavior can be useful, and thus the effect of modular neural networks is also explored. Results demonstrate that fitness rewarding individual behavior is superior to fitness rewarding team behavior, despite being applied to a cooperative task. However, the use of networks with multiple modules allows predators to discover intelligent behavior, regardless of which type of objectives are used.
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。
