mlsanityData to 7 Oct 2026

Interpretable and Explainable Logical Policies via Neurally Guided Symbolic Abstraction

arXiv 2306.01439 ↗First posted 2 Jun 2023cs.LG cs.AI cs.CLcited by 45

Not on the map. Why?

Abstract (arXiv)

The limited priors required by neural networks make them the dominating choice to encode and learn policies using reinforcement learning (RL). However, they are also black-boxes, making it hard to understand the agent's behaviour, especially when working on the image level. Therefore, neuro-symbolic RL aims at creating policies that are interpretable in the first place. Unfortunately, interpretability is not explainability. To achieve both, we introduce Neurally gUided Differentiable loGic policiEs (NUDGE). NUDGE exploits trained neural network-based agents to guide the search of candidate-weighted logic rules, then uses differentiable logic to train the logic agents. Our experimental evaluation demonstrates that NUDGE agents can induce interpretable and explainable policies while outperforming purely neural ones and showing good flexibility to environments of different initial states and problem sizes.

Key facts. Cited by 45 papers in the map (data through 7 Oct 2026). Builds on 30 of its 56 references that are in the map. First posted on arXiv 2 Jun 2023.

Builds on

30 of 56 references.

References · 30

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  3. 2017Axiomatic Attribution for Deep Networkscited by 3,350
  4. 2016Asynchronous Methods for Deep Reinforcement Learningcited by 2,218
  5. 2015Deep Reinforcement Learning with Double Q-learningcited by 1,704
  6. 2017Robust Adversarial Reinforcement Learningcited by 439
  7. 2017Soft-DTW: a Differentiable Loss Function for Time-Seriescited by 265
  8. 2017Learning Explanatory Rules from Noisy Datacited by 210
  9. 2018Programmatically Interpretable Reinforcement Learningcited by 192
  10. 2020SPACE: Unsupervised Object-Oriented Scene Representation via Spatial Attention and Decompositioncited by 190
  11. 2019Explainable Reinforcement Learning Through a Causal Lenscited by 177
  12. 2020Logical Neural Networkscited by 118
18 more
  1. 2020Right for the Right Concept: Revising Neuro-Symbolic Concepts by Interacting with their Explanationscited by 94
  2. 2018SDRL: Interpretable and Data-efficient Deep Reinforcement Learning Leveraging Symbolic Planningcited by 77
  3. 2018Relational Deep Reinforcement Learningcited by 72
  4. 2019Neural Logic Reinforcement Learningcited by 53
  5. 2017Deep Object-Centric Representations for Generalizable Robot Learningcited by 50
  6. 2021Inductive logic programming at 30cited by 46
  7. 2019An Inductive Synthesis Framework for Verifiable Reinforcement Learningcited by 39
  8. 2021Neuro-Symbolic Reinforcement Learning with First-Order Logiccited by 30
  9. 2021Differentiable Inductive Logic Programming for Structured Examplescited by 26
  10. 2021Adaptive Rational Activations to Boost Deep Reinforcement Learningcited by 23
  11. 2021Measuring Sample Efficiency and Generalization in Reinforcement Learning Benchmarks: NeurIPS 2020 Procgen Benchmarkcited by 23
  12. 2022Boosting Object Representation Learning via Motion and Object Continuitycited by 17
  13. 2017Mutual Alignment Transfer Learningcited by 16
  14. 2021Neuro-Symbolic Forward Reasoningcited by 16
  15. 2022GALOIS: Boosting Deep Reinforcement Learning via Generalizable Logic Synthesiscited by 16
  16. 2020KoGuN: Accelerating Deep Reinforcement Learning via Integrating Human Suboptimal Knowledgecited by 13
  17. 2022Symbolic Visual Reinforcement Learning: A Scalable Framework with Object-Level Abstraction and Differentiable Expression Searchcited by 9
  18. 2021Interpretable Model-based Hierarchical Reinforcement Learning using Inductive Logic Programmingcited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 18; 2025: 18; 2026: 7.

45 papers.

Sort:

By area:

  1. 2023OCAtari: Object-Centric Atari 2600 Reinforcement Learning Environmentscited by 30
  2. 2024Interpretable Concept Bottlenecks to Align Reinforcement Learning Agentscited by 23
  3. 2024Pix2Code: Learning to Compose Neural Visual Concepts as Programscited by 18
  4. 2024Interpretable and Editable Programmatic Tree Policies for Reinforcement Learningcited by 18
  5. 2025A Comprehensive Survey on Self-Interpretable Neural Networkscited by 18
  6. 2024End-to-End Neuro-Symbolic Reinforcement Learning with Textual Explanationscited by 17
  7. 2024Imperative Learning: A Self-supervised Neuro-Symbolic Learning Framework for Robot Autonomycited by 16
  8. 2024BlendRL: A Framework for Merging Symbolic and Neural Policy Learningcited by 14
  9. 2024Synthesizing Programmatic Reinforcement Learning Policies with Large Language Model Guided Searchcited by 13
  10. 2024HackAtari: Atari Learning Environments for Robust and Continual Reinforcement Learningcited by 11
  11. 2024LogiCity: Advancing Neuro-Symbolic AI with Abstract Urban Simulationcited by 8
  12. 2025Multimodal LLM-assisted Evolutionary Search for Programmatic Control Policiescited by 8
33 more
  1. 2025Reinforcement Learning Fine-Tuning Enhances Activation Intensity and Diversity in the Internal Circuitry of LLMscited by 8
  2. 2024Towards Symbolic XAI -- Explanation Through Human Understandable Logical Relationships Between Featurescited by 7
  3. 2024Understanding What Affects the Generalization Gap in Visual Reinforcement Learning: Theory and Empirical Evidencecited by 5
  4. 2024EXPIL: Explanatory Predicate Invention for Learning in Gamescited by 5
  5. 2024Mitigating Information Loss in Tree-Based Reinforcement Learning via Direct Optimizationcited by 5
  6. 2025NeuroStrata: Harnessing Neurosymbolic Paradigms for Improved Design, Testability, and Verifiability of Autonomous CPScited by 5
  7. 2024LICORICE: Label-Efficient Concept-Based Interpretable Reinforcement Learningcited by 4
  8. 2024Interpretable end-to-end Neurosymbolic Reinforcement Learning agentscited by 4
  9. 2025Neural DNF-MT: A Neuro-symbolic Approach for Learning Interpretable and Editable Policiescited by 4
  10. 2025Rule-Guided Reinforcement Learning Policy Evaluation and Improvementcited by 4
  11. 2025Reinforcement Learning with Physics-Informed Symbolic Program Priors for Zero-Shot Wireless Indoor Navigationcited by 4
  12. 2025Evaluating Interpretable Reinforcement Learning by Distilling Policies into Programscited by 3
  13. 2025Better Decisions through the Right Causal World Modelcited by 3
  14. 2025Learning from Less: Guiding Deep Reinforcement Learning with Differentiable Symbolic Planningcited by 3
  15. 2025Model Science: getting serious about verification, explanation and control of AI systemscited by 3
  16. 2023Scalable Semantic Non-Markovian Simulation Proxy for Reinforcement Learningcited by 2
  17. 2025Vejde: A Framework for Inductive Deep Reinforcement Learning Based on Factor Graph Color Refinementcited by 2
  18. 2025Towards autonomous normative multi-agent systems for Human-AI software engineering teamscited by 2
  19. 2026Learning Explicit Behavioral Models with Adaptive Questions and World-Model Probescited by 2
  20. 2025Inducing, Detecting and Characterising Neural Modules: A Pipeline for Functional Interpretability in Reinforcement Learningcited by 1
  21. 2025Human-Allied Relational Reinforcement Learningcited by 1
  22. 2024Towards a Research Community in Interpretable Reinforcement Learning: the InterpPol Workshopcited by 0
  23. 2024OCALM: Object-Centric Assessment with Language Modelscited by 0
  24. 2024LLM-Augmented Symbolic Reinforcement Learning with Landmark-Based Task Decompositioncited by 0
  25. 2025SALSA-RL: Stability Analysis in the Latent Space of Actions for Reinforcement Learningcited by 0
  26. 2025Semi-Gradient SARSA Routing with Theoretical Guarantee on Traffic Stability and Weight Convergencecited by 0
  27. 2025Disentangling Neural Disjunctive Normal Form Modelscited by 0
  28. 2026Boosting deep Reinforcement Learning using pretraining with Logical Optionscited by 0
  29. 2026GRAIL: Autonomous Concept Grounding for Neuro-Symbolic Reinforcement Learningcited by 0
  30. 2026Discovering Interpretable Multi-Parameter Control Policies for Evolutionary Algorithms Using Deep Reinforcement Learningcited by 0
  31. 2026Interpreting Neural Combinatorial Optimization via Evolving Programmatic Bottleneckscited by 0
  32. 2026From Black Box to Executable Logic: Explainable Reinforcement Learning through Prolog Expert Systemscited by 0
  33. 2026Interpretable reinforcement learning with decision-tree pruningcited by 0