Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2603.15054 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917345929199616 |
|---|---|
| author | Cheng, Ziyu Ren, Jinsheng Jiang, Zhouxian Li, Chenzhihang Shi, Rongye Liang, Bin Yang, Jun |
| author_facet | Cheng, Ziyu Ren, Jinsheng Jiang, Zhouxian Li, Chenzhihang Shi, Rongye Liang, Bin Yang, Jun |
| contents | Effective communication is pivotal for addressing complex collaborative tasks in multi-agent reinforcement learning (MARL). Yet, limited communication bandwidth and dynamic, intricate environmental topologies present significant challenges in identifying high-value communication partners. Agents must consequently select collaborators under uncertainty, lacking a priori knowledge of which partners can deliver task-critical information. To this end, we propose Interference-Aware K-Step Reachable Communication (IA-KRC), a novel framework that enhances cooperation via two core components: (1) a K-Step reachability protocol that confines message passing to physically accessible neighbors, and (2) an interference-prediction module that optimizes partner choice by minimizing interference while maximizing utility. Compared to existing methods, IA-KRC enables substantially more persistent and efficient cooperation despite environmental interference. Comprehensive evaluations confirm that IA-KRC achieves superior performance compared to state-of-the-art baselines, while demonstrating enhanced robustness and scalability in complex topological and highly dynamic multi-agent scenarios. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_15054 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Interference-Aware K-Step Reachable Communication in Multi-Agent Reinforcement Learning Cheng, Ziyu Ren, Jinsheng Jiang, Zhouxian Li, Chenzhihang Shi, Rongye Liang, Bin Yang, Jun Artificial Intelligence Effective communication is pivotal for addressing complex collaborative tasks in multi-agent reinforcement learning (MARL). Yet, limited communication bandwidth and dynamic, intricate environmental topologies present significant challenges in identifying high-value communication partners. Agents must consequently select collaborators under uncertainty, lacking a priori knowledge of which partners can deliver task-critical information. To this end, we propose Interference-Aware K-Step Reachable Communication (IA-KRC), a novel framework that enhances cooperation via two core components: (1) a K-Step reachability protocol that confines message passing to physically accessible neighbors, and (2) an interference-prediction module that optimizes partner choice by minimizing interference while maximizing utility. Compared to existing methods, IA-KRC enables substantially more persistent and efficient cooperation despite environmental interference. Comprehensive evaluations confirm that IA-KRC achieves superior performance compared to state-of-the-art baselines, while demonstrating enhanced robustness and scalability in complex topological and highly dynamic multi-agent scenarios. |
| title | Interference-Aware K-Step Reachable Communication in Multi-Agent Reinforcement Learning |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2603.15054 |