BriefGPT.xyz
Jul, 2022
StarCraft II中基于点集的无监督Hebbian学习
Unsupervised Hebbian Learning on Point Sets in StarCraft II
HTML
PDF
Beomseok Kang, Harshit Kumar, Saurabh Dash, Saibal Mukhopadhyay
TL;DR
本文介绍了一种新颖的Hebbian学习方法，以提取StarCraft II游戏单位中的点集的全局特征，并将其应用于预测点的移动，实验证明该模型比自监督学习方法具有更低的预测损失和更低的计算成本。
Abstract
Learning the evolution of real-time strategy (RTS) game is a challenging problem in artificial intelligent (AI) system. In this paper, we present a novel
hebbian learning method
to extract the global feature of point sets in
→