Bach2Bach: Generating Music Using A Deep Reinforcement Learning Approach

TL;DR

This paper introduces a deep reinforcement learning model for generating polyphonic music that maintains musical coherence and structure, utilizing a Bi-axial LSTM and DQN to improve exploration and global consistency.

Contribution

It presents a novel deep reinforcement learning architecture combining Bi-axial LSTM and DQN for polyphonic music generation, emphasizing global coherence and adherence to musical rules.

Findings

The model effectively generates coherent polyphonic music.

Quantitative and qualitative analyses show improved musical quality.

The approach outperforms traditional methods in maintaining musical structure.

Abstract

A model of music needs to have the ability to recall past details and have a clear, coherent understanding of musical structure. Detailed in the paper is a deep reinforcement learning architecture that predicts and generates polyphonic music aligned with musical rules. The probabilistic model presented is a Bi-axial LSTM trained with a pseudo-kernel reminiscent of a convolutional kernel. To encourage exploration and impose greater global coherence on the generated music, a deep reinforcement learning approach DQN is adopted. When analyzed quantitatively and qualitatively, this approach performs well in composing polyphonic music.