Bridging Training and Execution via Dynamic Directed Graph-Based Communication in Cooperative Multi-Agent Systems
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866916630045392896 |
|---|---|
| author | Zhang, Zhuohui He, Bin Cheng, Bin Li, Gang |
| author_facet | Zhang, Zhuohui He, Bin Cheng, Bin Li, Gang |
| contents | Multi-agent systems must learn to communicate and understand interactions between agents to achieve cooperative goals in partially observed tasks. However, existing approaches lack a dynamic directed communication mechanism and rely on global states, thus diminishing the role of communication in centralized training. Thus, we propose the Transformer-based graph coarsening network (TGCNet), a novel multi-agent reinforcement learning (MARL) algorithm. TGCNet learns the topological structure of a dynamic directed graph to represent the communication policy and integrates graph coarsening networks to approximate the representation of global state during training. It also utilizes the Transformer decoder for feature extraction during execution. Experiments on multiple cooperative MARL benchmarks demonstrate state-of-the-art performance compared to popular MARL algorithms. Further ablation studies validate the effectiveness of our dynamic directed graph communication mechanism and graph coarsening networks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_07397 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Bridging Training and Execution via Dynamic Directed Graph-Based Communication in Cooperative Multi-Agent Systems Zhang, Zhuohui He, Bin Cheng, Bin Li, Gang Multiagent Systems Multi-agent systems must learn to communicate and understand interactions between agents to achieve cooperative goals in partially observed tasks. However, existing approaches lack a dynamic directed communication mechanism and rely on global states, thus diminishing the role of communication in centralized training. Thus, we propose the Transformer-based graph coarsening network (TGCNet), a novel multi-agent reinforcement learning (MARL) algorithm. TGCNet learns the topological structure of a dynamic directed graph to represent the communication policy and integrates graph coarsening networks to approximate the representation of global state during training. It also utilizes the Transformer decoder for feature extraction during execution. Experiments on multiple cooperative MARL benchmarks demonstrate state-of-the-art performance compared to popular MARL algorithms. Further ablation studies validate the effectiveness of our dynamic directed graph communication mechanism and graph coarsening networks. |
| title | Bridging Training and Execution via Dynamic Directed Graph-Based Communication in Cooperative Multi-Agent Systems |
| topic | Multiagent Systems |
| url | https://arxiv.org/abs/2408.07397 |