Corpus ID: 3439214

SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient

@inproceedings{Yu2017SeqGANSG,
  title={SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient},
  author={Lantao Yu and W. Zhang and J. Wang and Y. Yu},
  booktitle={AAAI},
  year={2017}
}
As a new way of training generative models, Generative Adversarial Nets (GAN) that uses a discriminative model to guide the training of the generative model has enjoyed considerable success in generating real-valued data. [...] Key Method Modeling the data generator as a stochastic policy in reinforcement learning (RL), SeqGAN bypasses the generator differentiation problem by directly performing gradient policy update.Expand
1,270 Citations
ACtuAL: Actor-Critic Under Adversarial Learning
  • 3
  • PDF
Imitation Learning for Sentence Generation with Dilated Convolutions Using Adversarial Training
  • Highly Influenced
Toward learning better metrics for sequence generation training with policy gradient
  • 3
  • Highly Influenced
PolicyGAN: Training generative adversarial networks using policy gradient
TreeGAN: Syntax-Aware Sequence Generation with Generative Adversarial Networks
  • 12
  • Highly Influenced
  • PDF
Image Captioning using Adversarial Networks and Reinforcement Learning
  • 4
Adversarial Text Generation Without Reinforcement Learning
  • 12
  • PDF
Generative Adversarial Network Training is a Continual Learning Problem
  • 29
  • PDF
A Continuous Approach to Controllable Text Generation using Generative Adversarial Networks
  • 1
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 62 REFERENCES
Generative Adversarial Nets
  • 21,507
  • PDF
How (not) to Train your Generative Model: Scheduled Sampling, Likelihood, Adversary?
  • 187
  • Highly Influential
  • PDF
An Actor-Critic Algorithm for Sequence Prediction
  • 393
  • Highly Influential
  • PDF
Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks
  • 1,076
  • Highly Influential
  • PDF
Generalized Denoising Auto-Encoders as Generative Models
  • 373
  • PDF
Sequence to Sequence Learning with Neural Networks
  • 11,931
  • PDF
Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks
  • 1,571
  • PDF
Adam: A Method for Stochastic Optimization
  • 60,977
  • PDF
Learning deep generative models
  • 274
  • PDF
Data Generation as Sequential Decision Making
  • 33
  • Highly Influential
  • PDF
...
1
2
3
4
5
...