mlsanityData to 14 Oct 2026

Programmatically Interpretable Reinforcement Learning

arXiv 1804.02477 ↗First posted 6 Apr 2018cs.LG cs.AI cs.PLcited by 193

Not on the map. Why?

Cited by 42 in Deep reinforcement learning methods, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We present a reinforcement learning framework, called Programmatically Interpretable Reinforcement Learning (PIRL), that is designed to generate interpretable and verifiable agent policies. Unlike the popular Deep Reinforcement Learning (DRL) paradigm, which represents policies by neural networks, PIRL represents policies using a high-level, domain-specific programming language. Such programmatic policies have the benefits of being more easily interpreted than neural networks, and being amenable to verification by symbolic methods. We propose a new method, called Neurally Directed Program Search (NDPS), for solving the challenging nonsmooth optimization problem of finding a programmatic policy with maximal reward. NDPS works by first learning a neural policy network using DRL, and then performing a local search over programmatic policies that seeks to minimize a distance from this neural "oracle". We evaluate NDPS on the task of learning to drive a simulated car in the TORCS car-racing environment. We demonstrate that NDPS is able to discover human-readable policies that pass some significant performance bars. We also show that PIRL policies can have smoother trajectories, and can be more easily transferred to environments not encountered during training, than corresponding policies discovered by DRL.

Key facts. Cited by 193 papers in the map (data through 14 Oct 2026). First posted on arXiv 6 Apr 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2019: 2; 2020: 0; 2021: 35; 2022: 38; 2023: 36; 2024: 31; 2025: 21; 2026: 30.

193 papers.

Sort:

By area:

  1. 2024Mechanistic Interpretability for AI Safety -- A Reviewcited by 422
  2. 2021Interpretable Machine Learning: Fundamental Principles and 10 Grand Challengescited by 367
  3. 2022Toward Transparent AI: A Survey on Interpreting the Inner Structures of Deep Neural Networkscited by 129
  4. 2024WorldCoder, a Model-Based LLM Agent: Building World Models by Writing Code and Interacting with the Environmentcited by 107
  5. 2021A Survey on Interpretable Reinforcement Learningcited by 73
  6. 2021Compositional Reinforcement Learning from Logical Specificationscited by 67
  7. 2021Learning to Synthesize Programs as Interpretable and Generalizable Policiescited by 59
  8. 2023Datasets and Benchmarks for Offline Safe Reinforcement Learningcited by 59
  9. 2021Reinforcement Learning for Selective Key Applications in Power Systems: Recent Advances and Future Challengescited by 50
  10. 2023Interpretable and Explainable Logical Policies via Neurally Guided Symbolic Abstractioncited by 46
  11. 2024Generating Code World Models with Large Language Models Guided by Monte Carlo Tree Searchcited by 40
  12. 2021Counterfactual State Explanations for Reinforcement Learning Agents via Generative Deep Learningcited by 39
38 more
  1. 2023Explainable Deep Reinforcement Learning: State of the Art and Challengescited by 33
  2. 2024RL-GPT: Integrating Reinforcement Learning and Code-as-policycited by 32
  3. 2022A Survey of Explainable Reinforcement Learningcited by 31
  4. 2019Few-Shot Bayesian Imitation Learning with Logical Program Policiescited by 30
  5. 2021Explainable Reinforcement Learning for Broad-XAI: A Conceptual Framework and Surveycited by 24
  6. 2023Neurosymbolic Reinforcement Learning and Planning: A Surveycited by 24
  7. 2024Interpretable Concept Bottlenecks to Align Reinforcement Learning Agentscited by 23
  8. 2021ProTo: Program-Guided Transformer for Program-Guided Taskscited by 21
  9. 2021Connecting Attributions and QA Model Behavior on Realistic Counterfactualscited by 20
  10. 2023Hierarchical Programmatic Reinforcement Learning via Learning to Compose Programscited by 20
  11. 2024Interpretable and Editable Programmatic Tree Policies for Reinforcement Learningcited by 18
  12. 2024End-to-End Neuro-Symbolic Reinforcement Learning with Textual Explanationscited by 17
  13. 2021Inherently Explainable Reinforcement Learning in Natural Languagecited by 16
  14. 2022GALOIS: Boosting Deep Reinforcement Learning via Generalizable Logic Synthesiscited by 16
  15. 2023Structure in Deep Reinforcement Learning: A Survey and Open Problemscited by 16
  16. 2024Graph Reinforcement Learning for Combinatorial Optimization: A Survey and Unifying Perspectivecited by 16
  17. 2021Explainable Autonomous Robots: A Survey and Perspectivecited by 15
  18. 2024Dynamic Model Predictive Shielding for Provably Safe Reinforcement Learningcited by 15
  19. 2022POETREE: Interpretable Policy Learning with Adaptive Decision Treescited by 14
  20. 2022Survey on Fair Reinforcement Learning: Theory and Practicecited by 14
  21. 2024BlendRL: A Framework for Merging Symbolic and Neural Policy Learningcited by 14
  22. 2021Neurosymbolic Transformers for Multi-Agent Communicationcited by 13
  23. 2021Deep Interpretable Models of Theory of Mindcited by 13
  24. 2022Redefining Counterfactual Explanations for Reinforcement Learning: Overview, Challenges and Opportunitiescited by 13
  25. 2024Synthesizing Programmatic Reinforcement Learning Policies with Large Language Model Guided Searchcited by 13
  26. 2021Improving Human Sequential Decision-Making with Reinforcement Learningcited by 12
  27. 2022Explainability in reinforcement learning: perspective and positioncited by 11
  28. 2022What can we Learn Even From the Weakest? Learning Sketches for Programmatic Strategiescited by 11
  29. 2025A Snapshot of Influence: A Local Data Attribution Framework for Online Reinforcement Learningcited by 11
  30. 2021Discovering User-Interpretable Capabilities of Black-Box Planning Agentscited by 10
  31. 2023Causal Explanations for Sequential Decision-Making in Multi-Agent Systemscited by 10
  32. 2023Improving Unsupervised Visual Program Inference with Code Rewriting Familiescited by 10
  33. 2023Efficient Symbolic Policy Learning with Differentiable Symbolic Expressioncited by 10
  34. 2019From explanation to synthesis: Compositional program induction for learning from demonstrationcited by 9
  35. 2021Learning Symbolic Rules for Interpretable Deep Reinforcement Learningcited by 9
  36. 2021Programmatic Reward Design by Examplecited by 9
  37. 2022A Hierarchical Bayesian Approach to Inverse Reinforcement Learning with Symbolic Reward Machinescited by 9
  38. 2022A Survey on XAI for 5G and Beyond Security: Technical Aspects, Challenges and Research Directionscited by 9

50 most cited of 193 All 193 (JSON)