OptiGAN: Generative Adversarial Networks for Goal Optimized Sequence Generation

04/16/2020
by   Mahmoud Hossam, et al.
22

One of the challenging problems in sequence generation tasks is the optimized generation of sequences with specific desired goals. Existing sequential generative models mainly generate sequences to closely mimic the training data, without direct optimization according to desired goals or properties specific to the task. In this paper, we propose OptiGAN, a generative GAN-based model that incorporates both Generative Adversarial Networks and Reinforcement Learning (RL) to optimize desired goal scores using policy gradients. We apply our model to text and sequence generation, where our model is able to achieve higher scores out-performing other GAN and RL models, while not sacrificing output sample diversity.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/30/2017

Objective-Reinforced Generative Adversarial Networks (ORGAN) for Sequence Generation Models

In unsupervised data generation tasks, besides the generation of a sampl...
research
08/16/2018

Improving Conditional Sequence Generative Adversarial Networks by Stepwise Evaluation

Sequence generative adversarial networks (SeqGAN) have been used to impr...
research
07/04/2022

Disentangling Random and Cyclic Effects in Time-Lapse Sequences

Time-lapse image sequences offer visually compelling insights into dynam...
research
09/18/2016

SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient

As a new way of training generative models, Generative Adversarial Nets ...
research
12/10/2020

HpGAN: Sequence Search with Generative Adversarial Networks

Sequences play an important role in many engineering applications and sy...
research
11/09/2016

Sequence Tutor: Conservative Fine-Tuning of Sequence Generation Models with KL-control

This paper proposes a general method for improving the structure and qua...
research
10/31/2017

A SeqGAN for Polyphonic Music Generation

We propose an application of SeqGAN, generative adversarial networks for...

Please sign up or login with your details

Forgot password? Click here to reset