Multiscale Generative Models: Improving Performance of a Generative Model Using Feedback from Other Dependent Generative Models
This addresses the need for realistic multi-agent simulation in tasks like reinforcement learning, though it is an incremental step in modeling interactions.
The paper tackles the problem of monolithic generative models missing interactions in multi-agent systems by building multiple interacting GANs, where feedback from a higher-level GAN improves lower-level GAN performance, achieving gains across synthetic, time-series, and image domains.
Realistic fine-grained multi-agent simulation of real-world complex systems is crucial for many downstream tasks such as reinforcement learning. Recent work has used generative models (GANs in particular) for providing high-fidelity simulation of real-world systems. However, such generative models are often monolithic and miss out on modeling the interaction in multi-agent systems. In this work, we take a first step towards building multiple interacting generative models (GANs) that reflects the interaction in real world. We build and analyze a hierarchical set-up where a higher-level GAN is conditioned on the output of multiple lower-level GANs. We present a technique of using feedback from the higher-level GAN to improve performance of lower-level GANs. We mathematically characterize the conditions under which our technique is impactful, including understanding the transfer learning nature of our set-up. We present three distinct experiments on synthetic data, time series data, and image domain, revealing the wide applicability of our technique.