Adaptive Background Music for a Fighting Game: A Multi-Instrument Volume Modulation Approach

TL;DR

This paper introduces an adaptive background music system for a fighting game that dynamically adjusts instrument volumes based on game elements, improving AI performance using deep reinforcement learning with only audio input.

Contribution

It proposes a novel multi-instrument volume modulation approach for adaptive BGM in games, linked to game elements, and demonstrates its effectiveness with a blind deep RL AI.

Findings

AI performance improves with adaptive BGM

Adaptive BGM enhances game experience

Deep RL AI benefits from audio-only input

Abstract

This paper presents our work to enhance the background music (BGM) in DareFightingICE by adding an adaptive BGM. The adaptive BGM consists of five different instruments playing a classical music piece called "Air on G-String." The BGM adapts by changing the volume of the instruments. Each instrument is connected to a different element of the game. We then run experiments to evaluate the adaptive BGM by using a deep reinforcement learning AI that only uses audio as input (Blind DL AI). The results show that the performance of the Blind DL AI improves while playing with the adaptive BGM as compared to playing without the adaptive BGM.