Multi-Task Multi-Agent Reinforcement Learning via Skill Graphs

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhu, Guobin, Zhou, Rui, Ji, Wenkang, Zhang, Hongyin, Wang, Donglin, Zhao, Shiyu
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913933659471872
author Zhu, Guobin
Zhou, Rui
Ji, Wenkang
Zhang, Hongyin
Wang, Donglin
Zhao, Shiyu
author_facet Zhu, Guobin
Zhou, Rui
Ji, Wenkang
Zhang, Hongyin
Wang, Donglin
Zhao, Shiyu
contents Multi-task multi-agent reinforcement learning (MT-MARL) has recently gained attention for its potential to enhance MARL's adaptability across multiple tasks. However, it is challenging for existing multi-task learning methods to handle complex problems, as they are unable to handle unrelated tasks and possess limited knowledge transfer capabilities. In this paper, we propose a hierarchical approach that efficiently addresses these challenges. The high-level module utilizes a skill graph, while the low-level module employs a standard MARL algorithm. Our approach offers two contributions. First, we consider the MT-MARL problem in the context of unrelated tasks, expanding the scope of MTRL. Second, the skill graph is used as the upper layer of the standard hierarchical approach, with training independent of the lower layer, effectively handling unrelated tasks and enhancing knowledge transfer capabilities. Extensive experiments are conducted to validate these advantages and demonstrate that the proposed method outperforms the latest hierarchical MAPPO algorithms. Videos and code are available at https://github.com/WindyLab/MT-MARL-SG
format Preprint
id arxiv_https___arxiv_org_abs_2507_06690
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Multi-Task Multi-Agent Reinforcement Learning via Skill Graphs
Zhu, Guobin
Zhou, Rui
Ji, Wenkang
Zhang, Hongyin
Wang, Donglin
Zhao, Shiyu
Robotics
Multi-task multi-agent reinforcement learning (MT-MARL) has recently gained attention for its potential to enhance MARL's adaptability across multiple tasks. However, it is challenging for existing multi-task learning methods to handle complex problems, as they are unable to handle unrelated tasks and possess limited knowledge transfer capabilities. In this paper, we propose a hierarchical approach that efficiently addresses these challenges. The high-level module utilizes a skill graph, while the low-level module employs a standard MARL algorithm. Our approach offers two contributions. First, we consider the MT-MARL problem in the context of unrelated tasks, expanding the scope of MTRL. Second, the skill graph is used as the upper layer of the standard hierarchical approach, with training independent of the lower layer, effectively handling unrelated tasks and enhancing knowledge transfer capabilities. Extensive experiments are conducted to validate these advantages and demonstrate that the proposed method outperforms the latest hierarchical MAPPO algorithms. Videos and code are available at https://github.com/WindyLab/MT-MARL-SG
title Multi-Task Multi-Agent Reinforcement Learning via Skill Graphs
topic Robotics
url https://arxiv.org/abs/2507.06690