# Incorporating Relational Background Knowledge into Reinforcement Learning via Differentiable Inductive Logic Programming

arXiv: https://arxiv.org/abs/2003.10386 · HTML: https://mlsanity.com/paper/2003.10386/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Mar 2020.

## Built on by (most cited first, 12 of 12)

- [A Survey on Interpretable Reinforcement Learning](https://mlsanity.com/paper/2112.13112/) (2021)
- [Differentiable Logic Machines](https://mlsanity.com/paper/2102.11529/) (2021)
- [Structure in Deep Reinforcement Learning: A Survey and Open Problems](https://mlsanity.com/paper/2306.16021/) (2023)
- [Deep Explainable Relational Reinforcement Learning: A Neuro-Symbolic Approach](https://mlsanity.com/paper/2304.08349/) (2023)
- [Learning Symbolic Rules for Interpretable Deep Reinforcement Learning](https://mlsanity.com/paper/2103.08228/) (2021)
- [A Survey on Explainable Reinforcement Learning: Concepts, Algorithms, Challenges](https://mlsanity.com/paper/2211.06665/) (2022)
- [XRL-Bench: A Benchmark for Evaluating and Comparing Explainable Reinforcement Learning Techniques](https://mlsanity.com/paper/2402.12685/) (2024)
- [Neural Logic Networks for Interpretable Classification](https://mlsanity.com/paper/2508.08172/) (2025)
- [Deep Inductive Logic Programming meets Reinforcement Learning](https://mlsanity.com/paper/2308.16210/) (2023)
- [Efficient Open-world Reinforcement Learning via Knowledge Distillation and Autonomous Rule Discovery](https://mlsanity.com/paper/2311.14270/) (2023)
- [LLM-Augmented Symbolic Reinforcement Learning with Landmark-Based Task Decomposition](https://mlsanity.com/paper/2410.01929/) (2024)
- [Compositional Concept-Based Neuron-Level Interpretability for Deep Reinforcement Learning](https://mlsanity.com/paper/2502.00684/) (2025)

## Abstract (arXiv)

Relational Reinforcement Learning (RRL) can offers various desirable features. Most importantly, it allows for incorporating expert knowledge into the learning, and hence leading to much faster learning and better generalization compared to the standard deep reinforcement learning. However, most of the existing RRL approaches are either incapable of incorporating expert background knowledge (e.g., in the form of explicit predicate language) or are not able to learn directly from non-relational data such as image. In this paper, we propose a novel deep RRL based on a differentiable Inductive Logic Programming (ILP) that can effectively learn relational information from image and present the state of the environment as first order logic predicates. Additionally, it can take the expert background knowledge and incorporate it into the learning problem using appropriate predicates. The differentiable ILP allows an end to end optimization of the entire framework for learning the policy in RRL. We show the efficacy of this novel RRL framework using environments such as BoxWorld, GridWorld as well as relational reasoning for the Sort-of-CLEVR dataset.