ACtuAL: Actor-Critic Under Adversarial Learning

@article{Goyal2017ACtuALAU,
  title={ACtuAL: Actor-Critic Under Adversarial Learning},
  author={Anirudh Goyal and Nan Rosemary Ke and Alex Lamb and R. Devon Hjelm and Christopher Joseph Pal and Joelle Pineau and Yoshua Bengio},
  journal={ArXiv},
  year={2017},
  volume={abs/1711.04755}
}
Generative Adversarial Networks (GANs) are a powerful framework for deep generative modeling. Posed as a two-player minimax problem, GANs are typically trained end-to-end on real-valued data and can be used to train a generator of high-dimensional and realistic images. However, a major limitation of GANs is that training relies on passing gradients from the discriminator through the generator via back-propagation. This makes it fundamentally difficult to train GANs with discrete data, as… CONTINUE READING
23
Twitter Mentions

References

Publications referenced by this paper.
SHOWING 1-10 OF 40 REFERENCES

Similar Papers

Loading similar papers…