mlsanityData to 14 Oct 2026

Interpretable and Editable Programmatic Tree Policies for Reinforcement Learning

arXiv 2405.14956 ↗First posted 23 May 2024cs.AI cs.LGcited by 18

On the map: Deep reinforcement learning methods → Interpretable and logic-guided RL

Abstract (arXiv)

Deep reinforcement learning agents are prone to goal misalignments. The black-box nature of their policies hinders the detection and correction of such misalignments, and the trust necessary for real-world deployment. So far, solutions learning interpretable policies are inefficient or require many human priors. We propose INTERPRETER, a fast distillation method producing INTerpretable Editable tRee Programs for ReinforcEmenT lEaRning. We empirically demonstrate that INTERPRETER compact tree programs match oracles across a diverse set of sequential decision tasks and evaluate the impact of our design choices on interpretability and performances. We show that our policies can be interpreted and edited to correct misalignments on Atari games and to explain real farming strategies.

Key facts. Cited by 18 papers in the map (data through 14 Oct 2026). Placed in Interpretable and logic-guided RL, one of 15 directions in Deep reinforcement learning methods. Builds on 36 of its 56 references that are in the map. First posted on arXiv 23 May 2024.

Builds on

36 of 56 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024End-to-End Neuro-Symbolic Reinforcement Learning with Textual Explanations19 Mar
  2. 2024Interpretable Concept Bottlenecks to Align Reinforcement Learning Agents11 Jan

Other references · 34

  1. 2017Attention Is All You Needcited by 60,361
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  3. 2017Proximal Policy Optimization Algorithmscited by 15,215
  4. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,885
  5. 2013Playing Atari with Deep Reinforcement Learningcited by 3,274
  6. 2015Trust Region Policy Optimizationcited by 2,580
  7. 2015Deep Reinforcement Learning with Double Q-learningcited by 1,745
  8. 2019Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AIcited by 1,552
  9. 2018A Survey Of Methods For Explaining Black Box Modelscited by 973
  10. 2016The Mythos of Model Interpretabilitycited by 721
  11. 2019Interpretable machine learning: definitions, methods, and applicationscited by 305
  12. 2023Fast Segment Anythingcited by 290
22 more
  1. 2018Programmatically Interpretable Reinforcement Learningcited by 193
  2. 2020SPACE: Unsupervised Object-Oriented Scene Representation via Spatial Attention and Decompositioncited by 190
  3. 2018Verifiable Reinforcement Learning via Policy Extractioncited by 177
  4. 2020Making deep neural networks right for the right scientific reasons by interacting with their explanationscited by 142
  5. 2020Explainable Deep Learning: A Field Guide for the Uninitiatedcited by 127
  6. 2021Explainable AI (XAI): A Systematic Meta-Survey of Current Challenges and Future Opportunitiescited by 125
  7. 2021Self-Attention Between Datapoints: Going Beyond Individual Input-Output Pairs in Deep Learningcited by 113
  8. 2019CrossQ: Batch Normalization in Deep Reinforcement Learning for Greater Sample Efficiency and Simplicitycited by 95
  9. 2020Model Interpretability through the Lens of Computational Complexitycited by 75
  10. 2021A Survey on Interpretable Reinforcement Learningcited by 73
  11. 2020MurTree: Optimal Classification Trees via Dynamic Programming and Searchcited by 63
  12. 2023Interpretable and Explainable Logical Policies via Neurally Guided Symbolic Abstractioncited by 46
  13. 2021Iterative Bounding MDPs: Learning Interpretable Policies via Non-Interpretable Methodscited by 31
  14. 2022A Survey of Explainable Reinforcement Learningcited by 31
  15. 2023OCAtari: Object-Centric Atari 2600 Reinforcement Learning Environmentscited by 30
  16. 2022Quant-BnB: A Scalable Branch-and-Bound Method for Optimal Decision Trees with Continuous Featurescited by 20
  17. 2024Pix2Code: Learning to Compose Neural Visual Concepts as Programscited by 18
  18. 2022Boosting Object Representation Learning via Motion and Object Continuitycited by 17
  19. 2021Efficient Decompositional Rule Extraction for Deep Neural Networkscited by 11
  20. 2022Explainability Via Causal Self-Talkcited by 6
  21. 2023Breiman meets Bellman: Non-Greedy Decision Trees with MDPscited by 6
  22. 2023Assessing the Interpretability of Programmatic Policies with Large Language Modelscited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 8; 2025: 2; 2026: 8.

18 papers.

Sort:

By area:

  1. 2024BlendRL: A Framework for Merging Symbolic and Neural Policy Learningcited by 14
  2. 2024Synthesizing Programmatic Reinforcement Learning Policies with Large Language Model Guided Searchcited by 13
  3. 2024HackAtari: Atari Learning Environments for Robust and Continual Reinforcement Learningcited by 11
  4. 2025Multimodal LLM-assisted Evolutionary Search for Programmatic Control Policiescited by 8
  5. 2024EXPIL: Explanatory Predicate Invention for Learning in Gamescited by 5
  6. 2024Mitigating Information Loss in Tree-Based Reinforcement Learning via Direct Optimizationcited by 5
  7. 2024Interpretable end-to-end Neurosymbolic Reinforcement Learning agentscited by 4
  8. 2024SMOSE: Sparse Mixture of Shallow Experts for Interpretable Reinforcement Learning in Continuous Control Taskscited by 3
  9. 2025Deep Reinforcement Learning via Object-Centric Attentioncited by 2
  10. 2026REFLEX: Reflective Evolution from LLM Experiencecited by 2
  11. 2024OCALM: Object-Centric Assessment with Language Modelscited by 0
  12. 2026GRAIL: Autonomous Concept Grounding for Neuro-Symbolic Reinforcement Learningcited by 0
6 more
  1. 2026Hierarchical Support Vector State Partitioning for Distilling Black Box Reinforcement Learning Policiescited by 0
  2. 2026Critic-Driven Voronoi-Quantization for Distilling Deep RL Policies to Explainable Modelscited by 0
  3. 2026From Black Box to Executable Logic: Explainable Reinforcement Learning through Prolog Expert Systemscited by 0
  4. 2026ConceptTree: Bringing Semantic Transparency to Black-Box Decision Making for Robotic Manipulationcited by 0
  5. 2026dtControl2+varepsilon: Trading Optimality for Explainability in MDPs via Decision Treescited by 0
  6. 2026Interpretable reinforcement learning with decision-tree pruningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025"So, Tell Me About Your Policy...": Distillation of interpretable policies from Deep Reinforcement Learning agents
  2. 2025Towards Automated Semantic Interpretability in Reinforcement Learning via Vision-Language Models
  3. 2024Optimizing Interpretable Decision Tree Policies for Reinforcement Learning
  4. 2024Towards a Research Community in Interpretable Reinforcement Learning: the InterpPol Workshop
  5. 2025Evaluating Interpretable Reinforcement Learning by Distilling Policies into Programs
  6. 2024BET: Explaining Deep Reinforcement Learning through The Error-Prone Decisions
  7. 2025From Explainability to Interpretability: Interpretable Policies in Reinforcement Learning Via Model Explanation
  8. 2024Interpretable Modeling of Deep Reinforcement Learning Driven Scheduling