Generalised Domain Model Acquisition from Action Traces
Generalised Domain Model Acquisition from Action Traces
复制标题
从动作轨迹获取广义域模型
DOI：
10.1609/icaps.v21i1.13476
复制
发表时间：
2011
期刊：
影响因子：
--
通讯作者：
P. Gregory
中科院分区：
文献类型：
--
作者：
S. Cresswell;P. Gregory
为规划制定领域模型的一种方法是从示例动作序列中学习模型。LOCM系统证明了仅从示例动作序列中学习领域模型的可行性，而无需观察计划之前，期间或之后的状态。LOCM使用以对象为中心的表示，其中每个对象由单个参数化状态机表示。这使得它在学习符合该表示的领域时非常强大，但也有一些已知的领域不符合该表示。本文介绍了一种新的LOCM2算法，该算法将LOCM的域表示推广到允许多个参数化状态机表示单个对象。这扩展了可以学习适当领域模型的领域的覆盖范围。LOCM2算法通过测试领域学习来描述和评估，这些领域学习来自过去国际规划竞赛公布的结果。
One approach to the problem of formulating domain models for planning is to learn the models from example action sequences. The LOCM system demonstrated the feasibility of learning domain models from example action sequences only, with no observation of states before, during or after the plans. LOCM uses an object-centred representation, in which each object is represented by a single parameterised state machine. This makes it powerful for learning domains which fit within that representation, but there are some well-known domains which do not. This paper introduces LOCM2, a novel algorithm in which the domain representation of LOCM is generalised to allow multiple parameterised state machines to represent a single object. This extends the coverage of domains for which an adequate domain model can be learned. The LOCM2 algorithm is described and evaluated by testing domain learning from example plans from published results of past International Planning Competitions.