English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Generative Adversarial Networks (GAN) have emerged as a formidable AI tool togenerate realistic outputs based on training datasets. However, the challengeof exerting control over the generation process of GANs remains a significanthurdle. In this paper, we propose a novel methodology to address this issue byintegrating a reinforcement learning (RL) agent with a latent-space GAN(l-GAN), thereby facilitating the generation of desired outputs. Morespecifically, we have developed an actor-critic RL agent with a meticulouslydesigned reward policy, enabling it to acquire proficiency in navigating thelatent space of the l-GAN and generating outputs based on specified tasks. Tosubstantiate the efficacy of our approach, we have conducted a series ofexperiments employing the MNIST dataset, including arithmetic addition as anillustrative task. The outcomes of these experiments serve to validate ourmethodology. Our pioneering integration of an RL agent with a GAN modelrepresents a novel advancement, holding great potential for enhancinggenerative networks in the future.

Controlling the Latent Space of GANs through Reinforcement Learning: A Case Study on Task-based Image-to-Image Translation