PACT：面向多表型分组临时协作的表型感知对比团队表示
PACT: Phenotype-Aware Contrastive Team Representation for Multi-Phenotype Grouped Ad Hoc Teamwork
AI总结：
针对多智能体系统中需与多样表型陌生队友协作的MPG-AHT问题，提出PACT方法，经实验验证其在分布外评估与样本效率上均优于现有最优基线。
摘要：
在多智能体系统领域，学习与各种陌生队友协作是一项重大挑战。现有的临时协作方法通常驱动受控智能体与由同一奖励函数塑造的、具有单一协作表型的一组队友协作。然而在实际应用中，受控智能体需与来自不同组、从未协作过的、具有多样协作表型的陌生队友协作。我们将此形式化为多表型分组临时协作（MPG-AHT）问题，并提出表型感知对比团队表示（PACT）以解决该问题。PACT具备表型感知对比学习与关系推理能力，可准确区分协作表型并捕捉智能体间交互。在多表型协作任务上的大量实验表明，PACT平均优于当前最优基线，在分布外评估中平均提升21.0%，在样本效率上平均提升36.5%。
英文摘要：
Learning to collaborate with various unfamiliar teammates poses a great challenge in the domain of multi-agent systems. Existing ad hoc teamwork methods typically drive controlled agents to collaborate with a group of teammates exhibiting a single coordination phenotype shaped by the same reward function. However, in real-world applications, controlled agents should collaborate with unfamiliar teammates of diverse coordination phenotypes among groups that have never worked together. We formalize this as the Multi-Phenotype Grouped Ad Hoc Teamwork (MPG-AHT) problem, and propose Phenotype-Aware Contrastive Team Representation (PACT) to solve this problem. PACT is empowered with phenotype-aware contrastive learning and relational reasoning to accurately distinguish coordination phenotypes and capture inter-agent interactions. Extensive experiments on multi-phenotype collaboration tasks show that PACT outperforms state-of-the-art baselines on average, achieving a mean 21.0% gain in out-of-distribution evaluation and a mean 36.5% gain in sample efficiency.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
