Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

TUNING RECURRENT NEURAL NETWORKS WITH REINFORCEMENT LEARNING #43

Open
icoxfog417 opened this issue Nov 19, 2016 · 0 comments
Open

TUNING RECURRENT NEURAL NETWORKS WITH REINFORCEMENT LEARNING #43

icoxfog417 opened this issue Nov 19, 2016 · 0 comments

Comments

@icoxfog417
Copy link
Member

icoxfog417 commented Nov 19, 2016

一言でいうと

音楽を生成するRNNを、強化学習で学習させるという方法。actionは音符を選ぶことで、Rewardは実際の曲的に出現しうるか+音楽理論に沿っているか(いくつかの特徴量で設定)で与える。これにより、これまでより格段に音楽的に好ましくない性質は低減し、好ましい性質は高くすることができた。

論文リンク

https://arxiv.org/pdf/1611.02796v2.pdf

ブログ

https://magenta.tensorflow.org/blog/2016/11/09/tuning-recurrent-networks-with-reinforcement-learning/

著者/所属機関

Natasha Jaques, Shixiang Gu, Richard E. Turner, Douglas Eck

  • Google Brain, USA
  • Massachusetts Institute of Technology, USA
  • University of Cambridge, UK
  • Max Planck Institute for Intelligent Systems, Germany

概要

新規性・差分

手法

結果

コメント

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

No branches or pull requests

1 participant