arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1909.04256cs.AI
收藏

强化学习中时态逻辑公式的迁移

Transfer of Temporal Logic Formulas in Reinforcement Learning

Oden Institute for Computational Engineering and Sciences, University of Texas, Austin(德克萨斯大学奥斯汀分校奥登计算工程与科学研究所)

Zhe Xu, Ufuk Topcu

摘要:

将源任务的高级知识转移到目标任务是加速强化学习(RL)的有效途径。例如,命题逻辑和一阶逻辑已经被用作这种知识的表示。我们研究任务之间的知识转移,其中事件的时间很重要。我们把这种任务称为时间任务。我们通过逻辑可迁移性的概念将时间任务之间的相似性具体化,并在不同但相似的时间任务之间开发了一种迁移学习方法。首先,我们提出了一种推理技术,提取度量区间时序逻辑(MITL)公式顺序析取范式从标记的轨迹收集在RL的两个任务。如果通过这种推理确定逻辑可转移性,我们构造一个时间自动机的每个顺序的合取子公式的推断MITL公式从这两个任务。我们在扩展状态上执行RL,其中包括源任务的时间自动机的位置和时钟值。然后,我们在相应的组件(时钟,位置等)之间建立映射。的时间自动机,并根据建立的映射转移扩展的Q-函数。最后,我们对目标任务的扩展状态执行RL,从传输的扩展Q函数开始。我们在两个案例研究的结果表明,根据源任务和目标任务的相似程度,目标任务的采样效率可以通过在扩展状态空间中执行RL来提高一个数量级,并通过使用转移的扩展Q函数进一步提高另一个数量级。

英文摘要:

Transferring high-level knowledge from a source task to a target task is an effective way to expedite reinforcement learning (RL). For example, propositional logic and first-order logic have been used as representations of such knowledge. We study the transfer of knowledge between tasks in which the timing of the events matters. We call such tasks temporal tasks. We concretize similarity between temporal tasks through a notion of logical transferability, and develop a transfer learning approach between different yet similar temporal tasks. We first propose an inference technique to extract metric interval temporal logic (MITL) formulas in sequential disjunctive normal form from labeled trajectories collected in RL of the two tasks. If logical transferability is identified through this inference, we construct a timed automaton for each sequential conjunctive subformula of the inferred MITL formulas from both tasks. We perform RL on the extended state which includes the locations and clock valuations of the timed automata for the source task. We then establish mappings between the corresponding components (clocks, locations, etc.) of the timed automata from the two tasks, and transfer the extended Q-functions based on the established mappings. Finally, we perform RL on the extended state for the target task, starting with the transferred extended Q-functions. Our results in two case studies show, depending on how similar the source task and the target task are, that the sampling efficiency for the target task can be improved by up to one order of magnitude by performing RL in the extended state space, and further improved by up to another order of magnitude using the transferred extended Q-functions.

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。

↑