"Did You Hear That?" Learning to Play Video Games from Audio Cues
This work addresses a novel sensory modality for AI in gaming, though it is incremental as it builds on existing frameworks and provides preliminary results.
The paper tackles the problem of game-playing AI learning from audio cues instead of visual input, presenting initial experiments with Q-Learning agents in audio-specified games within the General Video Game AI framework.
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.