arXiv cs.MA· Qiyue Xia, J. Michael Herrmann·· 12 小时前AI 评分18
MIRL：用偏好引导多目标多智能体强化学习中的合作
Preference-Guided Cooperation in Multi-Objective Multi-Agent Reinforcement Learning
AI 导读
研究者提出 Meta-Gradient Informed Multi-Objective Multi-Agent Reinforcement Learning（MIRL），含静态 MIRL-S 与动态 MIRL-D 两个变体，通过目标级反事实信用分配和元梯度信息让智能体各自学习目标优先级、同时优化系统级目标。在多目标多粒子环境实验中，该方法相比基线提升了 Pareto 前沿质量，动态变体表现最强。
正文
Abstract:Multi-objective multi-agent reinforcement learning (MOMARL) addresses agent coordination and objective trade-offs simultaneously while optimising overall system performance. Existing work tends to treat multi-agent cooperation and multi-objective optimisation as largely independent components of a learning problem, which amounts to an exorbitant complexity except in trivial cases. We study here whether the structure provided by multiple objectives can itself be exploited to facilitate cooperation, rather than being treated as an additional optimisation challenge. We formulate MOMARL at both the team and individual levels and introduce objective-wise counterfactual credit assignment to evaluate each agent's contribution across the team objectives. We propose Meta-Gradient Informed Multi-Objective Multi-Agent Reinforcement Learning (MIRL), with static (MIRL-S) and dynamic (MIRL-D) variants. By incorporating meta-gradient information, MIRL enables agents to learn how to prioritise objectives individually while collectively optimising the system-level objective, allowing the multi-objective structure to directly guide cooperation. Experiments on a multi-objective multiple particle environment show that our methods improve Pareto-front quality over baselines, with the dynamic variant achieving the strongest performance.
| Comments: | 14 pages, 4 figures, 1 table (plus 3 figures, 3 tables, and 2 algorithms in the appendix) |
| Subjects: | Multiagent Systems (cs.MA); Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.35736 [cs.MA] |
| (or arXiv:2610.35736v1 [cs.MA] for this version) | |
| https://doi.org/10.48550/arXiv.2610.35736 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Qiyue Xia [view email]
[v1]
Mon, 26 Oct 2026 16:53:25 UTC (2,947 KB)
来源：arXiv cs.MA · arxiv.org