用度量学习快速识别新目标，无需重新训练。
GRAML: Goal Recognition As Metric Learning
- 将目标识别转化为嵌入空间的度量学习，使用Siamese网络
- 仅需每类目标一个示例，就能快速适应新目标
- 在多个环境上比现有方法更快更准，适合动态场景
目标识别（Goal Recognition, GR）是根据观测行为推断智能体目标的问题。近年来的数据驱动方法减少了对手工构建领域模型的需求，但只能处理预定义的目标集，且新增目标时需耗时训练。为实现自动建模并快速适应新目标，本文提出GRAML：目标识别作为度量学习。GRAML采用双塔网络，将GR建模为深度度量学习任务，通过RNN学习嵌入空间中的度量：不同目标的观测轨迹嵌入相距较远，相同目标的嵌入则相近。该度量在仅提供每类目标一个观测示例的情况下仍具高效适应能力。在多种环境上的评估表明，GRAML在速度、灵活性和运行时性能上均优于当前最优方法，同时保持高识别精度。
原文摘要 · Abstract (English)
Goal Recognition (GR) is the problem of recognizing an agent's objectives based on observed actions. Recent data-driven approaches for GR alleviate the need for costly, manually crafted domain models. However, these approaches can only reason about a pre-defined set of goals, and time-consuming training is needed for new emerging goals. To keep this model-learning automated while enabling quick adaptation to new goals, this paper introduces GRAML: Goal Recognition As Metric Learning. GRAML uses a Siamese network to treat GR as a deep metric learning task, employing an RNN that learns a metric over an embedding space, where the embeddings for observation traces leading to different goals are distant, and embeddings of traces leading to the same goals are close. This metric is especially useful when adapting to new goals, even if given just one example observation trace per goal. Evaluated on a versatile set of environments, GRAML shows speed, flexibility, and runtime improvements over the state-of-the-art GR while maintaining accurate recognition.
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。