mlsanityData to 7 Oct 2026

Learning Symbolic Rules for Interpretable Deep Reinforcement Learning

arXiv 2103.08228 ↗First posted 15 Mar 2021cs.AIcited by 9

Not on the map. Why?

Abstract (arXiv)

Recent progress in deep reinforcement learning (DRL) can be largely attributed to the use of neural networks. However, this black-box approach fails to explain the learned policy in a human understandable way. To address this challenge and improve the transparency, we propose a Neural Symbolic Reinforcement Learning framework by introducing symbolic logic into DRL. This framework features a fertilization of reasoning and learning modules, enabling end-to-end learning with prior symbolic knowledge. Moreover, interpretability is achieved by extracting the logical rules learned by the reasoning module in a symbolic rule space. The experimental results show that our framework has better interpretability, along with competing performance in comparison to state-of-the-art approaches.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 25 of its 37 references that are in the map. First posted on arXiv 15 Mar 2021.

Builds on

25 of 37 references.

References · 25

  1. 2017Attention Is All You Needcited by 59,932
  2. 2017Proximal Policy Optimization Algorithmscited by 14,441
  3. 2015High-Dimensional Continuous Control Using Generalized Advantage Estimationcited by 1,916
  4. 2015Deep Reinforcement Learning with Double Q-learningcited by 1,704
  5. 2015Prioritized Experience Replaycited by 1,070
  6. 2016The Mythos of Model Interpretabilitycited by 716
  7. 2016Hierarchical Deep Reinforcement Learning: Integrating Temporal Abstraction and Intrinsic Motivationcited by 282
  8. 2017Learning Explanatory Rules from Noisy Datacited by 210
  9. 2018Programmatically Interpretable Reinforcement Learningcited by 192
  10. 2019Explainable Reinforcement Learning Through a Causal Lenscited by 177
  11. 2018Verifiable Reinforcement Learning via Policy Extractioncited by 176
  12. 2019Neural Logic Machinescited by 144
13 more
  1. 2017Visualizing and Understanding Atari Agentscited by 141
  2. 2018SDRL: Interpretable and Data-efficient Deep Reinforcement Learning Leveraging Symbolic Planningcited by 77
  3. 2018Relational Deep Reinforcement Learningcited by 72
  4. 2016Graying the black box: Understanding DQNscited by 68
  5. 2019Neural Logic Reinforcement Learningcited by 53
  6. 2019Interestingness Elements for Explainable Reinforcement Learning: Understanding Agents' Capabilities and Limitationscited by 50
  7. 2020Turning 30: New Ideas in Inductive Logic Programmingcited by 42
  8. 2019Learn to Explain Efficiently via Neural Logic Inductive Learningcited by 38
  9. 2020Neural Logic Reasoningcited by 38
  10. 2016Chains of Reasoning over Entities, Relations, and Text using Recurrent Neural Networkscited by 37
  11. 2019Generation of Policy-Level Explanations for Reinforcement Learningcited by 37
  12. 2020Incorporating Relational Background Knowledge into Reinforcement Learning via Differentiable Inductive Logic Programmingcited by 12
  13. 2020Self-Supervised Discovering of Interpretable Features for Reinforcement Learningcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 2; 2023: 3; 2024: 1; 2025: 0; 2026: 2.

9 papers.

  1. 2023Neurosymbolic Reinforcement Learning and Planning: A Surveycited by 24
  2. 2022Explainability in reinforcement learning: perspective and positioncited by 11
  3. 2022Symbolic Visual Reinforcement Learning: A Scalable Framework with Object-Level Abstraction and Differentiable Expression Searchcited by 9
  4. 2023Goal Space Abstraction in Hierarchical Reinforcement Learning via Set-Based Reachability Analysiscited by 6
  5. 2023Learning Symbolic Rules over Abstract Meaning Representations for Textual Reinforcement Learningcited by 4
  6. 2021Online Grounding of Symbolic Planning Domains in Unknown Environmentscited by 3
  7. 2024SkillTree: Explainable Skill-Based Deep Reinforcement Learning for Long-Horizon Control Taskscited by 3
  8. 2026SymbXRL: Symbolic Explainable Deep Reinforcement Learning for Mobile Networkscited by 1
  9. 2026SIA: Symbolic Interpretability for Anticipatory Deep Reinforcement Learning in Network Controlcited by 1