无需预设伙伴，自动生成适应性队友，提升协作鲁棒性。
Unsupervised Partner Design Enables Robust Ad-hoc Teamwork
- 动态生成训练伙伴，按可学习性自动选择，无需预训练群体。
- 在多个任务中表现优于有无群体的基线方法，人机测试中得分更高。
- 适合需要灵活协作的多智能体系统，如游戏或机器人团队。
我们提出无监督伙伴设计（UPD），一种无需预设群体的多智能体强化学习方法，用于实现稳健的临时协作。UPD 实时生成训练伙伴，并基于可学习性准则自适应选择，避免了对预训练伙伴群体或手动调参的需求。该简单机制有效实现了伙伴多样性，并可在具备过程生成器时扩展为联合伙伴-环境选择。在基于关卡的觅食、Overcooked-AI 及 Overcooked 泛化挑战任务中，UPD 持续优于各类基于群体与无群体的基线方法。在人类-AI 用户研究中，经 UPD 训练的智能体获得更高回报，且被评价为更具适应性、更像人类、更不易令人沮丧，优于所有对比方法。
原文摘要 · Abstract (English)
We introduce Unsupervised Partner Design (UPD), a population-free multi-agent reinforcement learning method for robust ad-hoc teamwork. UPD generates training partners on-the-fly and selects them adaptively based on a learnability criterion, removing the need for pre-trained partner populations or manual parameter tuning. We show that this simple mechanism enables effective partner diversity and can be extended to joint partner-environment selection when a procedural level generator is available. Across Level-Based Foraging, Overcooked-AI, and the Overcooked Generalisation Challenge, UPD consistently achieves strong performance compared to both population-based and population-free baselines. In a human-AI user study, agents trained with UPD achieve higher returns and are rated as more adaptive, more human-like, and less frustrating than all evaluated baseline methods.
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。