SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient — mentioned by rryan

Mon, 06 Feb 2017 07:27:53 GMT

GANs are a general tool -- they just happen to get a lot of attention for generating images of stuff. Here's an example for generating sequences [1]. The example is language oriented, but ultimately GANs are interesting because you can use them to build a generator for an arbitrary data distribution. This can have many applications in engineering (to take a random example -- generating plausible looking chemical structures under a certain set of constraints). As with any ML application, you need to quantify your tolerance for "inaccuracy" (in a generative setting, how well the generated…

Paper and discussion history. A mention is not an endorsement.

SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient — mentioned by whataretensors

Tue, 06 Dec 2016 03:26:19 GMT

GANs work on real-valued data. The problem with sequence data, like text, is that the error gradient can't flow through the generator. There's some really great work being done called "Sequence GAN" that turns sequence generation into a RL problem. I'm not sure how successful they are, but it seems potentially powerful. https://arxiv.org/abs/1609.05473

Paper and discussion history. A mention is not an endorsement.

SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient · HackerPapers discussions

SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient — mentioned by rryan

SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient — mentioned by whataretensors