Multi-Agent Reinforcement Learning with Communication-Constrained Priors
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912957119594496 |
|---|---|
| author | Yang, Guang Yang, Tianpei Qiao, Jingwen Wu, Yanqing Huo, Jing Chen, Xingguo Gao, Yang |
| author_facet | Yang, Guang Yang, Tianpei Qiao, Jingwen Wu, Yanqing Huo, Jing Chen, Xingguo Gao, Yang |
| contents | Communication is one of the effective means to improve the learning of cooperative policy in multi-agent systems. However, in most real-world scenarios, lossy communication is a prevalent issue. Existing multi-agent reinforcement learning with communication, due to their limited scalability and robustness, struggles to apply to complex and dynamic real-world environments. To address these challenges, we propose a generalized communication-constrained model to uniformly characterize communication conditions across different scenarios. Based on this, we utilize it as a learning prior to distinguish between lossy and lossless messages for specific scenarios. Additionally, we decouple the impact of lossy and lossless messages on distributed decision-making, drawing on a dual mutual information estimatior, and introduce a communication-constrained multi-agent reinforcement learning framework, quantifying the impact of communication messages into the global reward. Finally, we validate the effectiveness of our approach across several communication-constrained benchmarks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_03528 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Multi-Agent Reinforcement Learning with Communication-Constrained Priors Yang, Guang Yang, Tianpei Qiao, Jingwen Wu, Yanqing Huo, Jing Chen, Xingguo Gao, Yang Artificial Intelligence Multiagent Systems Communication is one of the effective means to improve the learning of cooperative policy in multi-agent systems. However, in most real-world scenarios, lossy communication is a prevalent issue. Existing multi-agent reinforcement learning with communication, due to their limited scalability and robustness, struggles to apply to complex and dynamic real-world environments. To address these challenges, we propose a generalized communication-constrained model to uniformly characterize communication conditions across different scenarios. Based on this, we utilize it as a learning prior to distinguish between lossy and lossless messages for specific scenarios. Additionally, we decouple the impact of lossy and lossless messages on distributed decision-making, drawing on a dual mutual information estimatior, and introduce a communication-constrained multi-agent reinforcement learning framework, quantifying the impact of communication messages into the global reward. Finally, we validate the effectiveness of our approach across several communication-constrained benchmarks. |
| title | Multi-Agent Reinforcement Learning with Communication-Constrained Priors |
| topic | Artificial Intelligence Multiagent Systems |
| url | https://arxiv.org/abs/2512.03528 |