One approach to explaining the hierarchical levels of understanding within a machine learning model is the symbolic method of inductive logic programming (ILP), which is data efficient and capable of learning first-order logic rules that can entail data behaviour. A differentiable extension to ILP, so-called differentiable Neural Logic (dNL) networks, are able to learn Boolean functions as their neural architecture includes symbolic reasoning. We propose an application of dNL in the field of Relational Reinforcement Learning (RRL) to address dynamic continuous environments. This represents an extension of previous work in applying dNL-based ILP in RRL settings, as our proposed model updates the architecture to enable it to solve problems in continuous RL environments. The goal of this research is to improve upon current ILP methods for use in RRL by incorporating non-linear continuous predicates, allowing RRL agents to reason and make decisions in dynamic and continuous environments.

翻译：解释机器学习模型内部层次化理解的一种方法是采用符号化的归纳逻辑编程（ILP），该方法具有数据高效性，且能够学习蕴含数据行为的一阶逻辑规则。ILP的可微分扩展——即可微分神经逻辑（dNL）网络——因其神经架构包含符号推理能力，能够学习布尔函数。我们提出将dNL应用于关系强化学习（RRL）领域，以解决动态连续环境中的问题。这扩展了先前在RRL场景中应用基于dNL的ILP的研究工作，因为我们的模型更新了架构，使其能够解决连续RL环境中的问题。本研究的目标是通过引入非线性连续谓词来改进当前用于RRL的ILP方法，从而使RRL代理能够在动态和连续环境中进行推理与决策。