Unsupervised Hebbian Learning On Point Sets In Starcraft Ii

# Unsupervised Hebbian Learning on Point Sets in StarCraft II

**arXiv ID:** 2207.12323
**Authors:** Beomseok Kang, Harshit Kumar, Saurabh Dash, Saibal Mukhopadhyay
**Published:** 2022-07-13T13:09:48Z
**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 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.

## Skill Description

This skill is generated from the arXiv paper: Unsupervised Hebbian Learning on Point Sets in StarCraft II (2207.12323).

## How to Use

[To be filled in by the user or by future automation]

## References

- [arXiv:2207.12323](http://arxiv.org/abs/2207.12323v1)