# Bach2Bach: Generating Music Using A Deep Reinforcement Learning Approach

arXiv: https://arxiv.org/abs/1812.01060 · HTML: https://mlsanity.com/paper/1812.01060/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Dec 2018.

## Built on by (most cited first, 4 of 4)

- [MusicRL: Aligning Music Generation to Human Preferences](https://mlsanity.com/paper/2402.04229/) (2024)
- [A Survey on Deep Reinforcement Learning for Audio-Based Applications](https://mlsanity.com/paper/2101.00240/) (2021)
- [Diversity-Rewarded CFG Distillation](https://mlsanity.com/paper/2410.06084/) (2024)
- [BackgroundMellow: A Multi-Modal Cohesive Framework for Narrative-Driven Rich Cinematic Soundscape Generation](https://mlsanity.com/paper/2607.11364/) (2026)

## Abstract (arXiv)

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.