Unsupervised Grounding of Plannable First-Order Logic Representation from Images
Unsupervised Grounding of Plannable First-Order Logic Representation from Images
复制标题
图像中可规划一阶逻辑表示的无监督基础
DOI：
--
复制
发表时间：
2019
期刊：
影响因子：
--
通讯作者：
Masataro Asai
中科院分区：
文献类型：
--
作者：
Masataro Asai
最近，人们对获取强化学习社区中环境的关系结构越来越感兴趣。然而，由此产生的“关系”并不是离散的逻辑谓词，与经典的计划或目标识别等符号推理相容。与此同时，Latplan(Asai和Fukunaga 2018)弥合了深度学习感知系统和象征性古典规划师之间的差距。该系统的一个关键组件是名为状态自动编码器(SAE)的神经网络，它将基于图像的输入编码为与经典规划兼容的命题表示法。为了两全其美，我们提出了一阶状态自动编码器，这是一种无监督的体系结构，用于固定一阶逻辑谓词和事实。每个谓词通过接受可解释的参数并返回命题值来对对象之间的关系进行建模。在使用8Putle和照片逼真的块世界环境的实验中，我们表明：(1)所得到的谓词捕捉了可解释的关系(例如，空间关系)；(2)它们有助于获得环境的紧凑、抽象的模型；(3)所得到的模型与符号化的经典规划是兼容的。
Recently, there is an increasing interest in obtaining the relational structures of the environment in the Reinforcement Learning community. However, the resulting “relations” are not the discrete, logical predicates compatible with the symbolic reasoning such as classical planning or goal recognition. Meanwhile, Latplan (Asai and Fukunaga 2018) bridged the gap between deep-learning perceptual systems and symbolic classical planners. One key component of the system is a Neural Network called State AutoEncoder (SAE), which encodes an image-based input into a propositional representation compatible with classical planning. To get the best of both worlds, we propose First-Order State AutoEncoder, an unsupervised architecture for grounding the first-order logic predicates and facts. Each predicate models a relationship between objects by taking the interpretable arguments and returning a propositional value. In the experiment using 8Puzzle and a photo-realistic Blocksworld environment, we show that (1) the resulting predicates capture the interpretable relations (e.g., spatial), (2) they help to obtain the compact, abstract model of the environment, and finally, (3) the resulting model is compatible with symbolic classical planning.