The use of artificial neural network to compose music is a new computer composition method proposed in recent years. The advantage of this method is that it can process large-scale data in a relatively short time, greatly reducing the preparation work before computer composition and improving composition efficiency. However, there are still many problems that have not made obvious breakthroughs. For example, the yield is low, and a considerable proportion of the generated works have no appreciation value. They are completely random patchwork of notes and chords in the time dimension; the music produced is not pleasant, the melody is too simple and so on. In order to make the songs generated by the composition system more in line with the rules of music theory, this paper proposes a music generation model ACMN (Actor-Critic Music Network) based on the policy gradient method, which is characterized by the combination of reinforcement learning technology and neural network. Experiments show that, compared with the composition model without reinforcement learning technology, the ACMN model has more outstanding performance in terms of repetition rate and pleasantness.

Han Chunlei, Yu Jinming. Research and Implementation of Automatic Composition System Based on ACMN. Academic Journal of Computing & Information Science (2022), Vol. 5, Issue 4: 79-86. https://doi.org/10.25236/AJCIS.2022.050415.

[1] Alpen A. Techniques for algorithmic composition of music. 1995.

[2] Basset BA, Neto JJ. A stochastic musical composer based on adaptive algorithms. 1999.

[3] Zhang Yingli, Liu Hong, Ma Jingang. Research on Genetic Algorithm Composition System [J]. Information Technology and Informatization, 2005(5):106-108.

[4] Tian Mei, Huang Zhixing, Zhang Yougang. Artificial Intelligence Technology in Algorithmic Composition [J]. Journal of Sichuan Institute of Education, 2006, 22(z2): 165-166, 168.

[5] Gao Ting. Research and implementation of music melody generation algorithm based on deep learning [D]. Beijing University of Posts and Telecommunications, 2021.

[6] Jing Li. Research on spectrum allocation and AoI of Internet of Vehicles based on reinforcement learning [D]. Chongqing: Chongqing University, 2020.

[7] Hochreiter S and Schmidhuber J. Long short-term memory. [J]. Neural computation, 1997, 9(8): 1735-80.

[8] Bai Yong, Tie Yun, Jin Cong, et al. Research on intelligent composition based on reinforcement learning [J]. Artificial Intelligence, 2020(2):47-56.

[9] Ivo Grondman et al. A Survey of Actor-Critic Reinforcement Learning: Standard and Natural Policy Gradients [J]. IEEE Transactions on Human-Machine Systems, 2012, 42(6): 1291-1307.

[10] Mohammad Akbari, Jie Liang. Semi-Recurrent CNN-Based VAE-GAN for Sequential Data Generation. IEEE International Conference on Acoustics, Speech and Signal Processing, 2018.2321-2325.