mlsanityData to 14 Oct 2026

Interpretable Model-based Hierarchical Reinforcement Learning using Inductive Logic Programming

arXiv 2106.11417 ↗First posted 21 Jun 2021cs.LGcited by 8

Not on the map. Why?

Abstract (arXiv)

Recently deep reinforcement learning has achieved tremendous success in wide ranges of applications. However, it notoriously lacks data-efficiency and interpretability. Data-efficiency is important as interacting with the environment is expensive. Further, interpretability can increase the transparency of the black-box-style deep RL models and hence gain trust from the users. In this work, we propose a new hierarchical framework via symbolic RL, leveraging a symbolic transition model to improve the data-efficiency and introduce the interpretability for learned policy. This framework consists of a high-level agent, a subtask solver and a symbolic transition model. Without assuming any prior knowledge on the state transition, we adopt inductive logic programming (ILP) to learn the rules of symbolic state transitions, introducing interpretability and making the learned behavior understandable to users. In empirical experiments, we confirmed that the proposed framework offers approximately between 30% to 40% more data efficiency over previous methods.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 29 of its 44 references that are in the map. First posted on arXiv 21 Jun 2021.

Builds on

29 of 44 references.

References · 29

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2017Towards A Rigorous Science of Interpretable Machine Learningcited by 1,416
  3. 2019When to Trust Your Model: Model-Based Policy Optimizationcited by 773
  4. 2019Solving Rubik's Cube with a Robot Handcited by 734
  5. 2018Learning Dexterous In-Hand Manipulationcited by 687
  6. 2018Explaining Explanations: An Overview of Interpretability of Machine Learningcited by 508
  7. 2019A Survey on Explainable Artificial Intelligence (XAI): Towards Medical XAIcited by 404
  8. 2016Hierarchical Deep Reinforcement Learning: Integrating Temporal Abstraction and Intrinsic Motivationcited by 286
  9. 2018Model-Ensemble Trust-Region Policy Optimizationcited by 219
  10. 2017Learning Explanatory Rules from Noisy Datacited by 211
  11. 2018Programmatically Interpretable Reinforcement Learningcited by 193
  12. 2019Explainable Machine Learning for Scientific Insights and Discoveriescited by 166
17 more
  1. 2017End-to-End Differentiable Provingcited by 161
  2. 2019Neural-Symbolic Computing: An Effective Methodology for Principled Integration of Machine Learning and Reasoningcited by 151
  3. 2019Neural Logic Machinescited by 145
  4. 2020Explainable Reinforcement Learning: A Surveycited by 141
  5. 2018Hierarchical Imitation and Reinforcement Learningcited by 88
  6. 2018Leveraging Grammar and Reinforcement Learning for Neural Program Synthesiscited by 84
  7. 2018SDRL: Interpretable and Data-efficient Deep Reinforcement Learning Leveraging Symbolic Planningcited by 78
  8. 2020Learning programs by learning from failurescited by 73
  9. 2019Neural Logic Reinforcement Learningcited by 53
  10. 2018PEORL: Integrating Symbolic Planning and Hierarchical Reinforcement Learning for Robust Decision-Makingcited by 52
  11. 2020Turning 30: New Ideas in Inductive Logic Programmingcited by 42
  12. 2016Learning Dexterous Manipulation Policies from Experience and Imitationcited by 33
  13. 2017"Dave...I can assure you...that it's going to be all right..." -- A definition, case for, and survey of algorithmic assurances in human-autonomy trust relationshipscited by 22
  14. 2019Learning Algorithms via Neural Logic Networkscited by 17
  15. 2018Hierarchical Reinforcement Learning with Abductive Planningcited by 5
  16. 2018Robot Representation and Reasoning with Knowledge from Reinforcement Learningcited by 5
  17. 2019On Policy Learning Robust to Irreversible Events: An Application to Robotic In-Hand Manipulationcited by 5

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 3; 2024: 1; 2025: 2.

8 papers.

  1. 2023Interpretable and Explainable Logical Policies via Neurally Guided Symbolic Abstractioncited by 46
  2. 2023Structure in Deep Reinforcement Learning: A Survey and Open Problemscited by 16
  3. 2022Explainability in Deep Reinforcement Learning, a Review into Current Methods and Applicationscited by 6
  4. 2024Interpretability in Action: Exploratory Analysis of VPT, a Minecraft Agentcited by 4
  5. 2025A Survey of Reinforcement Learning for Optimization in Automationcited by 4
  6. 2025TAG: A Decentralized Framework for Multi-Agent Hierarchical Reinforcement Learningcited by 2
  7. 2022Interpretable Hidden Markov Model-Based Deep Reinforcement Learning Hierarchical Framework for Predictive Maintenance of Turbofan Enginescited by 1
  8. 2023Efficient Open-world Reinforcement Learning via Knowledge Distillation and Autonomous Rule Discoverycited by 1