Deep Inductive Logic Programming meets Reinforcement Learning

TL;DR

This paper introduces an extension of differentiable Neural Logic networks for relational reinforcement learning, enabling reasoning in dynamic continuous environments with non-linear predicates, advancing symbolic learning methods.

Contribution

It extends dNL-based ILP to handle continuous RL environments, integrating non-linear predicates for improved reasoning in dynamic settings.

Findings

Enhanced RL agent reasoning in continuous environments

Successful application of dNL in dynamic RL tasks

Improved decision-making with non-linear predicates

Abstract

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.