Bridging Training And Execution Via Dynamic Directed Graph-based Communication In Cooperative Multi-agent Systems
2024 · Zhuohui Zhang, Bin He, Bin Cheng, et al.
Abstract
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 coar
Authors
(none)
Tags
Stats
Related papers
- Asynchronous Cooperative Multi-agent Reinforcement Learning With Limited Communication (2025)0.00
- Transformer-based Scalable Multi-agent Reinforcement Learning For Networked Systems With Long-range Interactions (2025)0.00
- A Survey Of Multi-agent Deep Reinforcement Learning With Graph Neural Network-based Communication (2026)0.00
- Counterfactual Multi-agent Reinforcement Learning With Graph Convolution Communication (2020)0.00
- From Explicit Communication To Tacit Cooperation:a Novel Paradigm For Cooperative MARL (2023)3.58
- Towards Efficient Collaboration Via Graph Modeling In Reinforcement Learning (2024)0.00
- Bridging MARL To SARL: An Order-independent Multi-agent Transformer Via Latent Consensus (2026)0.00
- Inferring Latent Temporal Sparse Coordination Graph For Multi-agent Reinforcement Learning (2024)6.77