Double Distillation Network for Multi-Agent Reinforcement Learning
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866929699032137728 |
|---|---|
| author | Zhou, Yang Wang, Siying Chen, Wenyu Zhang, Ruoning Zhao, Zhitong Zhang, Zixuan |
| author_facet | Zhou, Yang Wang, Siying Chen, Wenyu Zhang, Ruoning Zhao, Zhitong Zhang, Zixuan |
| contents | Multi-agent reinforcement learning typically employs a centralized training-decentralized execution (CTDE) framework to alleviate the non-stationarity in environment. However, the partial observability during execution may lead to cumulative gap errors gathered by agents, impairing the training of effective collaborative policies. To overcome this challenge, we introduce the Double Distillation Network (DDN), which incorporates two distillation modules aimed at enhancing robust coordination and facilitating the collaboration process under constrained information. The external distillation module uses a global guiding network and a local policy network, employing distillation to reconcile the gap between global training and local execution. In addition, the internal distillation module introduces intrinsic rewards, drawn from state information, to enhance the exploration capabilities of agents. Extensive experiments demonstrate that DDN significantly improves performance across multiple scenarios. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_03125 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Double Distillation Network for Multi-Agent Reinforcement Learning Zhou, Yang Wang, Siying Chen, Wenyu Zhang, Ruoning Zhao, Zhitong Zhang, Zixuan Multiagent Systems Machine Learning Multi-agent reinforcement learning typically employs a centralized training-decentralized execution (CTDE) framework to alleviate the non-stationarity in environment. However, the partial observability during execution may lead to cumulative gap errors gathered by agents, impairing the training of effective collaborative policies. To overcome this challenge, we introduce the Double Distillation Network (DDN), which incorporates two distillation modules aimed at enhancing robust coordination and facilitating the collaboration process under constrained information. The external distillation module uses a global guiding network and a local policy network, employing distillation to reconcile the gap between global training and local execution. In addition, the internal distillation module introduces intrinsic rewards, drawn from state information, to enhance the exploration capabilities of agents. Extensive experiments demonstrate that DDN significantly improves performance across multiple scenarios. |
| title | Double Distillation Network for Multi-Agent Reinforcement Learning |
| topic | Multiagent Systems Machine Learning |
| url | https://arxiv.org/abs/2502.03125 |