MIRL：用多目标结构引导多智能体协作的新方法
Preference-Guided Cooperation in Multi-Objective Multi-Agent Reinforcement Learning
一篇多智能体强化学习论文，提出 MIRL 方法让智能体自己学着权衡多个目标，Pareto 前沿质量超过了基线，做 MARL 的可以看看。
这篇论文研究多目标多智能体强化学习（MOMARL），提出 Meta-Gradient Informed MOMARL（MIRL），包含静态 MIRL-S 和动态 MIRL-D 两个变体。方法引入 objective-wise counterfactual credit assignment，评估每个智能体对各团队目标的贡献。借助元梯度信息，智能体可以 individually 学习目标优先级，同时共同优化系统级目标。在多目标多粒子环境实验中，该方法在 Pareto 前沿质量上优于基线，其中动态变体 MIRL-D 表现最强。
Preference-Guided Cooperation in Multi-Objective Multi-Agent Reinforcement Learning
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.
