arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1810.01992cs.AIcs.LG
收藏

使用LSTM的动作模型获取

Action Model Acquisition using LSTM

Univ. Grenoble Alpes(格勒诺布尔阿尔卑斯大学);CNRS(法国国家科学研究中心);Grenoble INP(格勒诺布尔国立高等物理、数学与信息学院);LIG(格勒诺布尔信息学实验室)

Ankuj Arora, Humbert Fiorino, Damien Pellier, Sylvie Pesty

摘要:

在自动规划和调度(APS)领域,智能代理凭借需要一个行动模型(行动的蓝图,其交错执行实现系统状态的转换),以计划和解决现实世界的问题。然而,编码该模型变得越来越麻烦,并且从观察到的计划执行序列(训练数据)学习该模型更有效。虽然基本目标是随后从这个学习的模型中进行规划,但大多数方法都有不足之处,因为任何低于基础模型的完美重建的方法都会使其在某些领域无法使用。这项工作提出了一种新的方法,使用长短期记忆(LSTM)技术的收购的底层动作模型。我们使用LSTM的序列标签功能从穷举模型集中分离出与负责产生训练数据的模型相同的模型。这种隔离能力使我们的方法成为一种有效的方法。

英文摘要:

In the field of Automated Planning and Scheduling (APS), intelligent agents by virtue require an action model (blueprints of actions whose interleaved executions effectuates transitions of the system state) in order to plan and solve real world problems. It is, however, becoming increasingly cumbersome to codify this model, and is more efficient to learn it from observed plan execution sequences (training data). While the underlying objective is to subsequently plan from this learnt model, most approaches fall short as anything less than a flawless reconstruction of the underlying model renders it unusable in certain domains. This work presents a novel approach using long short-term memory (LSTM) techniques for the acquisition of the underlying action model. We use the sequence labelling capabilities of LSTMs to isolate from an exhaustive model set a model identical to the one responsible for producing the training data. This isolation capability renders our approach as an effective one.

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。

↑