让智能体学会与多种协作风格的陌生队友高效配合
PACT: Phenotype-Aware Contrastive Team Representation for Multi-Phenotype Grouped Ad Hoc Teamwork
- 用对比学习识别不同协作风格，捕捉团队互动关系
- 跨分布评估平均提升21.0%，样本效率提高36.5%
- 适合需要灵活应对异质队友的真实多智能体场景
在多智能体系统中，与各种不熟悉队友协作是一项重大挑战。现有自适应团队协作方法通常让可控智能体与一组由相同奖励函数塑造的单一协作表型队友合作。然而，在真实应用中，可控智能体应能与从未共事过的、具有多样化协作表型的团队协同工作。为此，我们提出多表型分组自适应协作（MPG-AHT）问题，并设计了表型感知对比团队表示（PACT）来解决该问题。PACT通过表型感知对比学习和关系推理，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平均优于现有最先进基线，在分布外评估中实现21.0%的性能提升，在样本效率上达到36.5%的增益。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。