ConventionPlay：面向鲁棒临时协作的能力受限训练
原标题：ConventionPlay: Capability-Limited Training for Robust Ad-Hoc Collaboration
AI 摘要
论文提出 ConventionPlay，一种基于强化学习的训练方法，让智能体在与不同适应能力的伙伴协作时，主动探测伙伴能遵循的约定，并引导团队采用更优的联合策略。现有方法只训练出被动适应伙伴固定约定的跟随者，而 ConventionPlay 通过构建包含不同适应程度伙伴的训练种群，使智能体学会区分何时应顺从、何时应引导。实验表明，在多种复杂临时协作场景中，该方法优于 FCP 等现有方法。
正文节选
ConventionPlay: Capability-Limited Training for Robust Ad-Hoc Collaboration Abstract Ad-hoc collaboration often requires agents to identify and adhere to some shared convention within a cooperative task. Existing work on reinforcement learning (RL) for ad-hoc collaboration focuses on training agents that adapt to the conventions established by their partners. These methods fail to consider the possibility that while some partners might follow only a single fixed convention, others may themselves