mlsanityData to 14 Oct 2026

Deep Inductive Logic Programming meets Reinforcement Learning

arXiv 2308.16210 ↗First posted 30 Aug 2023cs.LG cs.LO cs.SCcited by 1

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 13 of its 22 references that are in the map. First posted on arXiv 30 Aug 2023.

Builds on

13 of 22 references.

References · 13

  1. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,885
  2. 2013Playing Atari with Deep Reinforcement Learningcited by 3,274
  3. 2016Asynchronous Methods for Deep Reinforcement Learningcited by 2,258
  4. 2018Scalable agent alignment via reward modeling: a research directioncited by 447
  5. 2017Learning Explanatory Rules from Noisy Datacited by 211
  6. 2019Soft Actor-Critic for Discrete Action Settingscited by 174
  7. 2019Neural Logic Machinescited by 145
  8. 2019Neural Logic Reinforcement Learningcited by 53
  9. 2019Learn to Explain Efficiently via Neural Logic Inductive Learningcited by 38
  10. 2019Inductive Logic Programming via Differentiable Deep Neural Logic Networkscited by 25
  11. 2020Incorporating Relational Background Knowledge into Reinforcement Learning via Differentiable Inductive Logic Programmingcited by 12
  12. 2017Deep Abstract Q-Networkscited by 6
1 more
  1. 2020Solving The Lunar Lander Problem under Uncertainty using Reinforcement Learningcited by 3

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025Lattice Annotated Temporal (LAT) Logic for Non-Markovian Reasoningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024LLMs for Relational Reasoning: How Far are We?
  2. 2025Logic-RL: Unleashing LLM Reasoning with Rule-Based Reinforcement Learning
  3. 2024LLM-Augmented Symbolic Reinforcement Learning with Landmark-Based Task Decomposition
  4. 2026From Black Box to Executable Logic: Explainable Reinforcement Learning through Prolog Expert Systems
  5. 2026Differentiable Logic Programming to Mitigate Reasoning Shortcuts in Neurosymbolic Systems
  6. 2025Satisfiability Modulo Theory Meets Inductive Logic Programming
  7. 2025Neural DNF-MT: A Neuro-symbolic Approach for Learning Interpretable and Editable Policies
  8. 2025Accelerated Learning with Linear Temporal Logic using Differentiable Simulation