arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1909.05546cs.AI
收藏

从状态空间的结构学习规划的一阶符号表示

Learning First-Order Symbolic Representations for Planning from the Structure of the State Space

Universidad Simón Bolívar(西蒙·玻利瓦尔大学);ICREA(加泰罗尼亚高等研究院);Universitat Pompeu Fabra(庞培法布拉大学)

Blai Bonet, Hector Geffner

摘要:

开发灵活的人工智能系统的主要障碍之一是基于数据的学习者和基于模型的求解者之间的分裂。求解器,如经典的规划是非常灵活的,可以处理各种问题的实例和目标,但需要一阶的符号模型。另一方面,基于数据的学习器是鲁棒的,但不产生这样的表示。在这项工作中,我们解决这个分裂,显示如何使用的规划者的一阶符号表示可以从非符号输入,编码的状态空间的结构。表示学习问题被公式化为在一个共同但未知的一阶域上推断规划实例的问题,该一阶域解释了所观察到的状态空间的结构。这意味着推断出一个完整的一阶表示(即一般动作模式,关系符号和对象),它解释了观察到的状态空间结构。推理问题被转换为两级组合搜索,其中外层搜索一小组超参数的值,内层通过SAT求解,搜索一阶符号模型。该框架产生一般和正确的一阶表示的标准问题,如夹具,Blocksworld,和河内输入图编码的平面状态空间结构的一个实例。

英文摘要:

One of the main obstacles for developing flexible AI systems is the split between data-based learners and model-based solvers. Solvers such as classical planners are very flexible and can deal with a variety of problem instances and goals but require first-order symbolic models. Data-based learners, on the other hand, are robust but do not produce such representations. In this work we address this split by showing how the first-order symbolic representations that are used by planners can be learned from non-symbolic inputs that encode the structure of the state space. The representation learning problem is formulated as the problem of inferring planning instances over a common but unknown first-order domain that account for the structure of the observed state space. This means to infer a complete first-order representation (i.e. general action schemas, relational symbols, and objects) that explains the observed state space structures. The inference problem is cast as a two-level combinatorial search where the outer level searches for values of a small set of hyperparameters and the inner level, solved via SAT, searches for a first-order symbolic model. The framework is shown to produce general and correct first-order representations for standard problems like Gripper, Blocksworld, and Hanoi from input graphs that encode the flat state-space structure of a single instance.

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。

↑