STAND：面向交互式任务学习的自感知预条件诱导
STAND: Self-Aware Precondition Induction for Interactive Task Learning
AI总结：
STAND通过自感知学习机制，在交互式任务学习中实现高效且准确的预条件诱导，提升训练一致性和主动学习支持。
摘要：
在交互式任务学习（ITL）中，人工智能代理通过任务执行过程中提供的有限人类指令学习新能力。STAND是一种专为这些人机协同训练场景设计的数据高效规则预条件诱导方法。STAND的关键特性在于其自感知学习能力——它可以将准确的训练进度指标反馈给用户。STAND在小数据预条件诱导任务中优于XGBoost、决策树、随机森林和版本空间等流行方法，并在预测其在验证示例上的性能提升时间时具有高度准确性。在我们的评估中，我们发现STAND比其他模型在训练过程中表现出更单调的改进趋势，且错误复发率较低。STAND的这些特性支持更一致的训练体验，使人类指导员能够估计何时完成训练，并通过识别需要更多训练的困难区域提供主动学习支持。
英文摘要：
In interactive task learning (ITL), AI agents learn new capabilities from limited human instruction provided during task execution. STAND is a new method of data-efficient rule precondition induction specifically designed for these human-in-the-loop training scenarios. A key feature of STAND is its self-awareness of its own learning -- it can provide accurate metrics of training progress back to users. STAND beats popular methods like XGBoost, decision trees, random forests, and version spaces at small-data precondition induction tasks, and is highly accurate at estimating when its performance improves on holdout examples. In our evaluations, we find that STAND shows more monotonic improvement than other models with low rates of error recurrence. These features of STAND support a more consistent training experience, enabling human instructors to estimate when they are finished training and providing active-learning support by identifying trouble spots where more training is required.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
