Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2410.23393 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916461919862784 |
|---|---|
| author | Chen, Qiliang Heydari, Babak |
| author_facet | Chen, Qiliang Heydari, Babak |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_23393 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Resource Governance in Networked Systems via Integrated Variational Autoencoders and Reinforcement Learning Chen, Qiliang Heydari, Babak Machine Learning Artificial Intelligence Multiagent Systems 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. |
| title | Resource Governance in Networked Systems via Integrated Variational Autoencoders and Reinforcement Learning |
| topic | Machine Learning Artificial Intelligence Multiagent Systems |
| url | https://arxiv.org/abs/2410.23393 |