发表机构
KAIST（韩国科学技术院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对具身环境中伙伴部分可观测导致的协调难题，提出PIP方法，利用联合视角VAE和伙伴状态信念网络推断伙伴意图，在三个基准及人类评估中取得最优性能。
AI 中文摘要
具身环境中的零样本协调要求在与伙伴间歇性脱离视线的情况下采取行动，这使得现有方法面临伙伴表示模糊和隐藏伙伴状态不确定的问题。我们提出“预测伙伴意图”（PIP）方法以共同应对这些挑战。PIP使用联合视角变分自编码器（Joint-view VAE），从两个智能体局部观测的并集中提取更丰富的训练时证据，形成仅凭局部观测即可获得的伙伴表示。伙伴状态信念网络进一步从自我智能体的交互历史中推断伙伴的隐藏位置和行为倾向。我们在Burrito-PO、Overcooked-PO和一个Melting Pot基底上评估PIP，并在Burrito-PO中进行人类评估。PIP在所有三个基准中取得了比较方法中最高的平均性能。人类评估和诊断分析进一步支持与未见伙伴的协调，以及两个组件在伙伴遮挡情况下的贡献。
英文摘要
Zero-shot coordination in embodied settings requires acting while the partner is intermittently out of view, leaving existing methods with ambiguous partner representations and uncertainty over hidden partner states. We propose Predicting Intention of Partner (PIP) to jointly address these challenges. PIP uses a Joint-view VAE to distill richer training-time evidence from the union of both agents' local observations into a partner representation available from local observations alone. Partner-state Belief networks further infer the partner's hidden location and behavioral tendencies from the ego agent's interaction history. We evaluate PIP in Burrito-PO, Overcooked-PO, and a Melting Pot substrate, together with a human evaluation in Burrito-PO. PIP attains the highest mean performance among the compared methods across all three benchmarks. Human evaluation and diagnostic analyses further support coordination with unseen partners and the contributions of both components under partner occlusion.
Commentspreprint
