… to train GANs for discrete sequence generation without resorting to an … generator’s distribution
and the empirical distribution over the training data without sampling from the generator, …

… Thus, we use policy gradients to train the generator based on a discriminator that can … fake
discrete samples. We propose a framework for generative adversarial sequence generation …

… applying adversarial training strategies to discrete sequence … sequence generation method,
SeqGAN, to effectively train generative adversarial nets for structured sequences generation …

… We also show how this core algorithm can be combined with several variance reduction
techniques to form the full MaliGAN algorithm for discrete sequence generation. …

… The generation of discrete … the GAN framework to sequential data [Yu et al., 2017] and
extend it towards domain-specific rewards. To increase the stability of the adversarial training, we …

… generating discrete data by an adversarial approach in which there is no need to pass the
gradient to the generator… manner in which each new generator is defined based on the last …

… However, generating discrete data is a challenge. This work presents an adversarial
training based correlated discrete data (CDD) generation model. It also details an approach for …

… We propose an application of sequence generative adversarial networks (SeqGAN),
which are generative adversarial networks for discrete sequence generation, for creating …

… Although the purpose of SeqGAN is to generate discrete sequential data, it opened the door
to other GANs in generating continuous sequential and time series data. The authors use a …

… SeqGAN, outperforming both models in almost all metrics, while the authors concluded that
they could effectively process discrete sequences through the actor-critic training algorithm. …