论文标题
无监督的Hebbian学习在Starcraft II中的点集
Unsupervised Hebbian Learning on Point Sets in StarCraft II
论文作者
论文摘要
学习实时策略（RTS）游戏的演变是人工智能（AI）系统中的一个具有挑战性的问题。在本文中，我们提出了一种新颖的Hebbian学习方法，用于提取Starcraft II游戏单元中的积分集的全球特征，以及其用于预测点的运动的应用。我们的模型包括编码器，LSTM和解码器，我们使用无监督的学习方法训练编码器。我们介绍了神经元活动意识学习的概念，并结合了K-Winner-Takes-all。神经元活动的最佳值是数学得出的，并且实验支持该概念在下游任务上的有效性。与自我监督的学习相比，我们的HEBBIAN学习规则受益于损失较低的预测。同样，与基于框架的方法相比，我们的模型可大大节省计算成本，例如激活和失败。
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 StarCraft II game units, and its application to predict the movement of the points. Our model includes encoder, LSTM, and decoder, and we train the encoder with the unsupervised learning method. We introduce the concept of neuron activity aware learning combined with k-Winner-Takes-All. The optimal value of neuron activity is mathematically derived, and experiments support the effectiveness of the concept over the downstream task. Our Hebbian learning rule benefits the prediction with lower loss compared to self-supervised learning. Also, our model significantly saves the computational cost such as activations and FLOPs compared to a frame-based approach.
