最大容许奖励机
Maximally Permissive Reward Machines
AI总结：
针对现有基于单规划的奖励机灵活性不足的问题，提出基于目标偏序规划集合成最大容许奖励机的方法，理论与实验均证明其能让智能体获得更高奖励。
摘要：
奖励机可用于为时序扩展任务和行为定义奖励。指定“具有信息性的”奖励机可能颇具挑战性。解决该问题的一种方式是利用AI规划等技术，根据学习环境的高层抽象描述生成奖励机。然而，以往基于规划的方法均基于单个（序列或偏序）规划生成奖励机，无法为学习智能体提供最大灵活性。本文提出了一种基于目标的偏序规划集合来合成奖励机的新方法。我们证明，使用此类“最大容许”奖励机进行学习，所获奖励高于使用基于单个规划的奖励机（RMs）的学习效果。我们还给出了实验结果，表明我们的方法在实际应用中比单规划方法能获得更高奖励，从而支撑了我们的理论结论。
英文摘要：
Reward machines allow the definition of rewards for temporally extended tasks and behaviors. Specifying "informative" reward machines can be challenging. One way to address this is to generate reward machines from a high-level abstract description of the learning environment, using techniques such as AI planning. However, previous planning-based approaches generate a reward machine based on a single (sequential or partial-order) plan, and do not allow maximum flexibility to the learning agent. In this paper we propose a new approach to synthesising reward machines which is based on the set of partial order plans for a goal. We prove that learning using such "maximally permissive" reward machines results in higher rewards than learning using RMs based on a single plan. We present experimental results which support our theoretical claims by showing that our approach obtains higher rewards than the single-plan approach in practice.
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。
