论文标题
神经NID规则
Neural NID Rules
论文作者
论文摘要
抽象的对象属性及其关系深深植根于人类的常识，即使在新颖但受到熟悉的物理定律支配的情况下，也可以预测世界的动态。基于模型的强化学习中的标准机器学习模型不足以以这种方式概括。受嘈杂的不确定性Dectic（NID）规则的经典框架的启发，我们在此介绍了Neural NID，该方法可以学习抽象对象属性和对象之间与适当正则化的图形神经网络之间的关系。我们验证神经NID在简单基准上的更大概括能力，专门设计用于评估模型所学的过渡动力学。
Abstract object properties and their relations are deeply rooted in human common sense, allowing people to predict the dynamics of the world even in situations that are novel but governed by familiar laws of physics. Standard machine learning models in model-based reinforcement learning are inadequate to generalize in this way. Inspired by the classic framework of noisy indeterministic deictic (NID) rules, we introduce here Neural NID, a method that learns abstract object properties and relations between objects with a suitably regularized graph neural network. We validate the greater generalization capability of Neural NID on simple benchmarks specifically designed to assess the transition dynamics learned by the model.
