Work

Unsupervised Hebbian Learning on Point Sets in StarCraft II

Year: 2022

Type: conference-paper

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 a point set 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.

Source: 2022 International Joint Conference on Neural Networks (IJCNN)

DOI: 10.1109/ijcnn55064.2022.9892259

Authors: Beomseok Kang, Harshit Kumar, Saurabh Dash, Saibal Mukhopadhyay

Institution: Georgia Institute of Technology

Language: English

Topic: Artificial Intelligence in Games

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funder: Office of Naval Research

Award: G790648140