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

Realistic fine-grained multi-agent simulation of real-world complex systemsis crucial for many downstream tasks such as reinforcement learning. Recentwork has used generative models (GANs in particular) for providinghigh-fidelity simulation of real-world systems. However, such generative modelsare often monolithic and miss out on modeling the interaction in multi-agentsystems. In this work, we take a first step towards building multipleinteracting generative models (GANs) that reflects the interaction in realworld. We build and analyze a hierarchical set-up where a higher-level GAN isconditioned on the output of multiple lower-level GANs. We present a techniqueof using feedback from the higher-level GAN to improve performance oflower-level GANs. We mathematically characterize the conditions under which ourtechnique is impactful, including understanding the transfer learning nature ofour set-up. We present three distinct experiments on synthetic data, timeseries data, and image domain, revealing the wide applicability of ourtechnique.

Multiscale Generative Models: Improving Performance of a Generative Model Using Feedback from Other Dependent Generative Models