发表机构
University of California, Merced（加州大学默塞德分校）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究揭示多智能体Transformer策略在排列鲁棒性评估中的陷阱，提出结合动作坍缩诊断，并发现弱等变性正则化可在保持动作多样性的同时提升鲁棒性。
AI 中文摘要
Transformer策略因其自注意力机制能够建模智能体之间的交互，在多智能体机器人学习中颇具吸引力。然而，多智能体团队是无序的，而Transformer通常将智能体作为有序的令牌序列进行处理。我们研究了这种不匹配如何在智能体顺序排列下影响协作导航策略。我们的结果表明，仅凭较低的排列误差可能具有误导性：策略看似鲁棒，可能仅仅是因为所有智能体选择了相同的动作。因此，我们使用排列一致性度量和动作坍缩诊断（包括动作多样性、相同动作比例和最大动作频率）来评估策略。PPO-ID基线产生非坍缩行为，但仍对顺序敏感，而强等变性正则化仍可能诱导同质行为。弱等变性惩罚在N=3个智能体的团队中提高了鲁棒性，同时保留了更多样化的动作，而N=4个智能体的团队则需要显著更小的正则化权重。这些发现表明，多智能体Transformer策略不仅应通过回报和排列鲁棒性来评估，还应检查其是否维持非坍缩、差异化的多智能体行为。
英文摘要
Transformer policies are attractive for multi-agent robot learning because self-attention can model interactions among agents. However, multi-agent teams are unordered, while transformers typically process agents as ordered token sequences. We study how this mismatch affects cooperative navigation policies under agent-order permutations. Our results show that low permutation error alone can be misleading: policies may appear robust simply because all agents choose the same action. We therefore evaluate policies using both permutation-consistency metrics and action-collapse diagnostics, including action diversity, same-action fraction, and maximum action frequency. A PPO-ID baseline yields non-collapsed behavior but remains order-sensitive, while strong equivariance regularization can still induce homogeneous behavior. A weak equivariance penalty improves the robustness while preserving more diverse actions for teams with \(N=3\) agents, whereas teams with \(N=4\) agents require substantially smaller regularization weights. These findings suggest that multi-agent transformer policies should be evaluated not only by return and permutation robustness, but also by whether they maintain non-collapsed, differentiated multi-agent behavior.
