Neural Architecture Search with Reinforcement Learning ​

← Back to topic

Authors: Barret Zoph, Quoc V. Le
Year: 2017
Journal: ICLR
DOI: 10.48550/arXiv.1611.01578
Publisher: https://arxiv.org/abs/1611.01578

Keywords: nas, rl

Abstract ​

We use a recurrent network to generate the model descriptions of neural networks and train this RNN with reinforcement learning to maximize the expected accuracy.

Cite this paper ​

@misc{nasrl2017,
  title  = {Neural Architecture Search with Reinforcement Learning},
  author = {Barret Zoph, Quoc V. Le},
  year   = {2017},
  journal = {ICLR},
  doi    = {10.48550/arXiv.1611.01578},
  url    = {https://doi.org/10.48550/arXiv.1611.01578},
}

Source files ​

• metadata.json
• paper.bib