Focusing Influence Mechanism for Multi-Agent Reinforcement Learning

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Park, Yisak, Lee, Sunwoo, Han, Seungyul
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866913113126731776
author Park, Yisak
Lee, Sunwoo
Han, Seungyul
author_facet Park, Yisak
Lee, Sunwoo
Han, Seungyul
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2506_19417
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Focusing Influence Mechanism for Multi-Agent Reinforcement Learning
Park, Yisak
Lee, Sunwoo
Han, Seungyul
Machine Learning
Multiagent Systems
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.
title Focusing Influence Mechanism for Multi-Agent Reinforcement Learning
topic Machine Learning
Multiagent Systems
url https://arxiv.org/abs/2506.19417