信号时序逻辑引导的学徒学习
Signal Temporal Logic-Guided Apprenticeship Learning
AI总结：
针对含时序依赖子目标的任务中学徒学习受演示质量限制的问题，提出将信号时序逻辑规范编码为图并定义时态度量以优化奖励与策略推断的方法，可大幅减少学习控制策略所需的演示数量。
摘要：
学徒学习的关键在于有效学习奖励函数，并据此从用户演示中学习控制策略。尤其困难的场景是目标任务包含多个存在时序依赖关系的子目标。推断得到的奖励函数及对应策略的质量通常受限于演示的质量，对二者的推断效果不佳会引发不理想的结果。在本文中，我们展示了如何将描述高层任务目标的时序逻辑规范编码到图中，定义一种基于时序的度量指标，用于推理演示者与智能体学习者的行为，从而提升推断得到的奖励函数与策略的质量。通过在多组不同的机械臂仿真任务上开展实验，我们证明所提框架大幅降低了学习控制策略所需的演示数量，克服了现有研究的缺陷。
英文摘要：
Apprenticeship learning crucially depends on effectively learning rewards, and hence control policies from user demonstrations. Of particular difficulty is the setting where the desired task consists of a number of sub-goals with temporal dependencies. The quality of inferred rewards and hence policies are typically limited by the quality of demonstrations, and poor inference of these can lead to undesirable outcomes. In this letter, we show how temporal logic specifications that describe high level task objectives, are encoded in a graph to define a temporal-based metric that reasons about behaviors of demonstrators and the learner agent to improve the quality of inferred rewards and policies. Through experiments on a diverse set of robot manipulator simulations, we show how our framework overcomes the drawbacks of prior literature by drastically improving the number of demonstrations required to learn a control policy.
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。
