Surprise-Guided Search for Learning Task Specifications from Demonstrations

Surprise-Guided Search for Learning Task Specifications from Demonstrations
复制标题

从演示中惊喜引导搜索学习任务规范

DOI:
--
复制
发表时间:
2022
期刊:
影响因子:
--
通讯作者:
S. Seshia
S. Seshia
中科院分区:
--
文献类型:
--
作者:
Marcell Vazquez;Ameesh Shah;Gil Lederman;S. Seshia

文献摘要

参考文献

被引文献

相似文献

本文认为,从专家演示中,学习临时任务规格,例如自动机和临时逻辑。 1)(可计算的)有限数量的任务;编码任务;(3)离散的解决方案空间 - 通常由(蛮力)枚举来克服这些障碍计划者和标记示例的任务采样器。通过猜想的示例,我们在确定性有限自动机描述的任务中提供了DISS的具体实现,并表明Diss能够有效地从一个或两个专家演示中识别任务。
This paper considers the problem of learning temporal task specifications, e.g. automata and temporal logic, from expert demonstrations. Task specifications are a class of sparse memory augmented rewards with explicit support for temporal and Boolean composition. Three features make learning temporal task specifications difficult: (1) the (countably) infinite number of tasks under consideration; (2) an a-priori ignorance of what memory is needed to encode the task; and (3) the discrete solution space - typically addressed by (brute force) enumeration. To overcome these hurdles, we propose Demonstration Informed Specification Search (DISS) : a family of algorithms requiring only black box access to a maximum entropy planner and a task sampler from labeled examples. DISS then works by alternating between conjecturing labeled examples to make the provided demonstrations less surprising and sampling tasks consistent with the conjectured labeled examples. We provide a concrete implementation of DISS in the context of tasks described by Deterministic Finite Automata, and show that DISS is able to efficiently identify tasks from only one or two expert demonstrations.
DOI: --
发表时间: 2021-11
期刊: ArXiv
影响因子: --
作者:
David Abel;Will Dabney;A. Harutyunyan;Mark K. Ho;M. Littman;Doina Precup;Satinder Singh
通讯作者: David Abel;Will Dabney;A. Harutyunyan;Mark K. Ho;M. Littman;Doina Precup;Satinder Singh
DOI: --
发表时间: 2018
期刊: Thirty-third Conference on Neural Information Processing Systems (NeurIPS
影响因子: --
作者:
VazquezChanlatte, Marcell;Jha, Susmit;Tiwari, Ashish;Seshia, Sanjit
通讯作者: Seshia, Sanjit
通过 GLTL 实现与环境无关的任务规范
DOI: --
发表时间: 2017
期刊: arXiv.org
影响因子: --
作者:
Littman, Michael L.;Topcu, Ufuk;Fu, Jie;Isbell, Charles;Wen, Min;MacGlashan, James
通讯作者: MacGlashan, James
通过从次优演示中学习时序逻辑公式来解释多阶段任务
DOI: --
发表时间: 2020
期刊: Robotics science and systems
影响因子: --
作者:
Chou, Glen;Ozay, Necmiye;Berenson, Dmitry
通讯作者: Berenson, Dmitry
使用基于逻辑的贝叶斯意图推理对移动机器人进行预测运行时监控
DOI: 10.1109/icra48506.2021.9561193
发表时间: 2021
期刊: 2021 IEEE International Conference on Robotics and Automation (ICRA
影响因子: --
作者:
Yoon, Hansol;Sankaranarayanan, Sriram
通讯作者: Sankaranarayanan, Sriram