# "Did You Hear That?" Learning to Play Video Games from Audio Cues

## TL;DR

This paper explores training game-playing AI agents solely on audio cues, expanding existing frameworks to include sound-based information and demonstrating initial results with simple learning agents.

## Contribution

It introduces a novel approach to game AI by incorporating audio cues, expanding game description languages, and providing a new API for audio-based learning.

## Key findings

- Initial experiments with Q-Learning agents show promise
- Audio-based game environments can be effectively designed
- Framework extensions enable audio perception in game AI

## Abstract

Game-playing AI research has focused for a long time on learning to play video games from visual input or symbolic information. However, humans benefit from a wider array of sensors which we utilise in order to navigate the world around us. In particular, sounds and music are key to how many of us perceive the world and influence the decisions we make. In this paper, we present initial experiments on game-playing agents learning to play video games solely from audio cues. We expand the Video Game Description Language to allow for audio specification, and the General Video Game AI framework to provide new audio games and an API for learning agents to make use of audio observations. We analyse the games and the audio game design process, include initial results with simple Q~Learning agents, and encourage further research in this area.