AI Paper Atlas

Research map / Reinforcement learning / Offline RL

RL-Duet: Online Music Accompaniment Generation Using Deep Reinforcement Learning

Nan Jiang, Sheng Jin, Zhiyao Duan, Changshui Zhang

AAAI 2020 · Reinforcement learning › Offline RL · approach: Diffusion models for offline decision making · 47 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Train the generation policy with RL-Duet rather than MLEOnline accompaniment generation · Subjective paired comparisonvotes preferring generated music: 58.42%Improved
Use RL-Duet rather than MLEOnline accompaniment generation · Bach Chorale test setPCH earth moving distance: 0.0067 -> 0.0057Improved
Use RL-Duet rather than MLEOnline accompaniment generation · Bach Chorale test setNLH earth moving distance: 0.039 -> 0.042Mixed
Use the multi-hold pitch representation instead of single-hold (ablation)RL-Duet generation model · Music generationdiversityImproved
Use the multi-hold pitch representation instead of single-hold (ablation)Reward models (b), (c), and (d) · Music generationrhythmic naturalnessHurt
Replace the transplanted SequenceTutor rules with RL-Duet's learned reward approachOnline accompaniment generation · Subjective user studygeneration qualityImproved

Later papers that compared with this method

1 later accepted paper reports RL-Duet as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy