计算机科学
生成语法
对抗制
序列(生物学)
人工智能
生成对抗网络
深度学习
遗传学
生物
作者
Gabriel Lima Guimaraes,Benjamín Sánchez-Lengeling,Pedro Luis Cunha Farias,Alán Aspuru‐Guzik
出处
期刊:Cornell University - arXiv
日期:2017-01-01
被引量:437
标识
DOI:10.48550/arxiv.1705.10843
摘要
In unsupervised data generation tasks, besides the generation of a sample based on previous observations, one would often like to give hints to the model in order to bias the generation towards desirable metrics. We propose a method that combines Generative Adversarial Networks (GANs) and reinforcement learning (RL) in order to accomplish exactly that. While RL biases the data generation process towards arbitrary metrics, the GAN component of the reward function ensures that the model still remembers information learned from data. We build upon previous results that incorporated GANs and RL in order to generate sequence data and test this model in several settings for the generation of molecules encoded as text sequences (SMILES) and in the context of music generation, showing for each case that we can effectively bias the generation process towards desired metrics.
科研通智能强力驱动
Strongly Powered by AbleSci AI