Abstract:Cooperative multi-agent reinforcement learning (MARL) under sparse rewards remains fundamentally challenging because agents often fail to concentrate their influence, leading to insufficiently coordinated exploration. To address this, we propose the Focusing Influence Mechanism (FIM), a framework that encourages agents to focus their influence on under-explored parts of the state space through an entropy-based criterion, while leveraging eligibility traces to enable multiple agents to consistently align and sustain their influence on the same parts of the state space when beneficial, thereby promoting coordinated and persistent joint behavior. By emphasizing under-explored regions of the state space, FIM facilitates more efficient and structured exploration even under extremely sparse rewards. Across diverse MARL benchmarks, FIM consistently improves cooperative performance over strong baselines.
| Comments: | 9 technical page followed by references and appendix |
| Subjects: | Machine Learning (cs.LG); Multiagent Systems (cs.MA) |
| Cite as: | arXiv:2506.19417 [cs.LG] |
| (or arXiv:2506.19417v2 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2506.19417 arXiv-issued DOI via DataCite |
From: Seungyul Han [view email]
[v1]
Tue, 24 Jun 2025 08:35:15 UTC (6,209 KB)
[v2]
Mon, 11 May 2026 20:15:11 UTC (39,490 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。