Niching Agents in The Core

📅 2026-09-10
📈 Citations: 0
✨ Influential: 0
📄 PDF
🤖 AI Summary
研究通过在特定子环境中划分代理,利用The Core算法的局部交互、锦标赛选择、交叉和变异方法,进化出更成功的自主控制代理。
📝 Abstract
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.
Problem

Research questions and friction points this paper is trying to address.

Niching Agents
The Core
Competitive Co-evolution
Xpilot Video Game
Sub-environments
Innovation

Methods, ideas, or system contributions that make the work stand out.

Niching Agents
Competitive Co-evolution
Tournament Selection
💼 Related Jobs
No related jobs found.
G
Gary B. Parker
Connecticut College, New London CT 06320-4125, USA
Jim O'Connor
Jim O'Connor
Connecticut College
Game AIRoboticsArtificial IntelligenceEvolutionary Computation
J
John Asaro
Connecticut College, New London CT 06320-4125, USA