arXiv：cs.AI· Jinnyeong Yang, Yuhwan Jeong, Hoyong Kwon, Minseok Kim, Jihun Kim, Kuk-Jin Yoon·· 6 小时前AI 评分31
PIP：通过预测伙伴意图实现部分可观测下的零样本协调
Partially Observable Zero-shot coordination by Predicting Intention of Partner
AI 导读
研究者提出 Predicting Intention of Partner（PIP），用于解决具身场景中伙伴间歇性不可见时的零样本协调问题。PIP 用 Joint-view VAE 将双方局部观测的并集蒸馏为仅凭自身局部观测即可获得的伙伴表示，并用伙伴状态 Belief 网络从交互历史推断伙伴的隐藏位置与行为倾向。
正文
Abstract: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.
| Comments: | preprint |
| Subjects: | Artificial Intelligence (cs.AI); Multiagent Systems (cs.MA) |
| Cite as: | arXiv:2610.08142 [cs.AI] |
| (or arXiv:2610.08142v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.08142 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Jinnyeong Yang [view email]
[v1]
Tue, 6 Oct 2026 10:55:06 UTC (1,851 KB)
来源：arXiv：cs.AI · arxiv.org