arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2207.04479cs.AIcs.CLcs.LG
收藏

基于部分STRIPS模型的ML黑箱规划

Scaling up ML-based Black-box Planning with Partial STRIPS Models

Aalborg University(奥尔堡大学);ServiceNow Research(ServiceNow研究院)

Matias Greco, Álvaro Torralba, Jorge A. Baier, Hector Palacios

摘要:

一种流行的顺序决策方法是执行基于模拟器的搜索,并使用机器学习(ML)方法(如策略学习)进行指导。另一方面,如果有一个完整的声明性模型,模型松弛算法可以有效地指导搜索。在这项工作中,我们考虑如何从业者可以提高ML为基础的黑盒规划设置一个完整的符号模型不可用。我们表明,指定一个不完整的CNOPS模型,只描述了问题的一部分,使使用松弛算法。我们在几个规划领域的研究结果表明,这是一种有效的方法来改善基于ML的黑盒规划,而不仅仅是收集更多的数据或调整ML架构。

英文摘要:

A popular approach for sequential decision-making is to perform simulator-based search guided with Machine Learning (ML) methods like policy learning. On the other hand, model-relaxation heuristics can guide the search effectively if a full declarative model is available. In this work, we consider how a practitioner can improve ML-based black-box planning on settings where a complete symbolic model is not available. We show that specifying an incomplete STRIPS model that describes only part of the problem enables the use of relaxation heuristics. Our findings on several planning domains suggest that this is an effective way to improve ML-based black-box planning beyond collecting more data or tuning ML architectures.

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。

↑