@article{Jiang_Jin_Duan_Zhang_2020, title={RL-Duet: Online Music Accompaniment Generation Using Deep Reinforcement Learning}, volume={34}, url={https://ojs.aaai.org/index.php/AAAI/article/view/5413}, DOI={10.1609/aaai.v34i01.5413}, abstractNote={<p>This paper presents a deep reinforcement learning algorithm for online accompaniment generation, with potential for real-time interactive human-machine duet improvisation. Different from offline music generation and harmonization, online music accompaniment requires the algorithm to respond to human input and generate the machine counterpart in a sequential order. We cast this as a reinforcement learning problem, where the generation agent learns a policy to generate a musical note (action) based on previously generated context (state). The key of this algorithm is the well-functioning reward model. Instead of defining it using music composition rules, we learn this model from monophonic and polyphonic training data. This model considers the compatibility of the machine-generated note with both the machine-generated context and the human-generated context. Experiments show that this algorithm is able to respond to the human part and generate a melodic, harmonic and diverse machine part. Subjective evaluations on preferences show that the proposed algorithm generates music pieces of higher quality than the baseline method.</p>}, number={01}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Jiang, Nan and Jin, Sheng and Duan, Zhiyao and Zhang, Changshui}, year={2020}, month={Apr.}, pages={710-718} }