发表机构
Connecticut College（康涅狄格学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究在 The Core 竞争性协同进化算法中引入小生境机制，将智能体限定于特定环境子集，实验证明其优于全局及跨子环境小生境化的智能体。
AI 中文摘要
The Core 是一种独特的竞争性协同进化算法，它允许智能体在无需传统适应度函数的情况下进化出自主控制能力。智能体通过局部交互（包括锦标赛选择、交叉和变异）进行进化，通过进化出更好的控制器来产生后代。先前的研究已表明 The Core 能够进化出能够在 Xpilot 视频游戏中执行战斗和导航任务的智能体。本研究在此前提基础上进行扩展，将智能体小生境化到 The Core 最初测试环境的特定子集。我们的结果表明，与针对整个系统进行小生境化的智能体以及针对不同子环境进行小生境化的智能体相比，小生境化智能体具有更强的成功能力。
英文摘要
The Core is a unique competitive co-evolution algorithm that allows agents to evolve autonomous control without utilizing a traditional fitness function. The agents evolve via local interactions through tournament selection, crossover, and mutation, producing offspring by evolving better controllers. Previous works have shown The Core's ability to evolve agents capable of combat and navigation in the Xpilot video game. This research expands upon that premise by niching agents to specific subsets of the original environment The Core was tested in. Our results demonstrate the niched agents capacity for success over agents niched to the entire system and agents niched to different sub-environments.
Journal refProceedings of the 17th International Conference on Evolutionary Computation Theory and Applications Part 2 (2025) 259-268
DOI：10.1007/978-3-032-15635-8_16
