Resource Governance in Networked Systems via Integrated Variational Autoencoders and Reinforcement Learning

TL;DR

This paper presents a novel framework combining variational autoencoders and reinforcement learning to optimize resource management and network structure adaptation in multi-agent systems, demonstrating superior performance and strategic insights.

Contribution

It introduces an integrated VAE-RL approach capable of managing large action spaces for dynamic network structure optimization.

Findings

Outperforms baseline methods in various scenarios

Reveals effective strategies through learned behaviors

Demonstrates adaptability in complex environments

Abstract

We introduce a framework that integrates variational autoencoders (VAE) with reinforcement learning (RL) to balance system performance and resource usage in multi-agent systems by dynamically adjusting network structures over time. A key innovation of this method is its capability to handle the vast action space of the network structure. This is achieved by combining Variational Auto-Encoder and Deep Reinforcement Learning to control the latent space encoded from the network structures. The proposed method, evaluated on the modified OpenAI particle environment under various scenarios, not only demonstrates superior performance compared to baselines but also reveals interesting strategies and insights through the learned behaviors.