[论文] Learning Coordinated Preference for Multi-Objective Multi-Agent Reinfo...

论文概要

研究领域: MA
作者: Pengxin Wang, Lihao Guo, Yi Xie
发布时间: 2026-06-12
arXiv: 2606.14693

中文摘要

协作多目标多智能体强化学习（MOMARL）建模在多个潜在冲突目标下的团队决策。在这种情况下，冲突不仅出现在目标之间，还出现在具有不同观察、角色和贡献的智能体之间。我们提出了偏好协调多智能体策略优化（PCMA），它学习协调的智能体特定偏好，以实现智能体间的互补权衡。理论上，我们将协作MOMARL表述为团队最优博弈，并表明在适当条件下，偏好多样性可以通过一阶改进分解诱导团队改进。在多个协作MOMA环境和实际交通控制场景上的实验表明，PCMA提高了性能和权衡协调。

原文摘要

Cooperative multi-objective multi-agent reinforcement learning (MOMARL) models team decision making under multiple, potentially conflicting objectives. In this setting, conflicts arise not only across objectives but also across agents with different observations, roles, and contributions. We propose Preference Coordinated Multi-agent Policy Optimization (PCMA), which learns coordinated agent-specific preferences to enable complementary trade-offs among agents. Theoretically, we formulate cooperative MOMARL as a team-optimal game and show that, under suitable conditions, preference diversity can induce team improvement through a first-order improvement decomposition. Experiments on multiple cooperative MOMA environments and a practical traffic-control scenario show that PCMA improves both p...

自动采集于 2026-06-16

#论文 #arXiv #MA #小凯