mlsanityData to 7 Oct 2026

End-to-End Neuro-Symbolic Reinforcement Learning with Textual Explanations

arXiv 2403.12451 ↗First posted 19 Mar 2024cs.AIcited by 17

Not on the map. Why?

Abstract (arXiv)

Neuro-symbolic reinforcement learning (NS-RL) has emerged as a promising paradigm for explainable decision-making, characterized by the interpretability of symbolic policies. NS-RL entails structured state representations for tasks with visual observations, but previous methods cannot refine the structured states with rewards due to a lack of efficiency. Accessibility also remains an issue, as extensive domain knowledge is required to interpret symbolic policies. In this paper, we present a neuro-symbolic framework for jointly learning structured states and symbolic policies, whose key idea is to distill the vision foundation model into an efficient perception module and refine it during policy learning. Moreover, we design a pipeline to prompt GPT-4 to generate textual explanations for the learned policies and decisions, significantly reducing users' cognitive load to understand the symbolic policies. We verify the efficacy of our approach on nine Atari tasks and present GPT-generated explanations for policies and decisions.

Key facts. Cited by 17 papers in the map (data through 7 Oct 2026). Builds on 33 of its 47 references that are in the map. First posted on arXiv 19 Mar 2024.

Builds on

33 of 47 references.

References · 33

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2023Sparks of Artificial General Intelligence: Early experiments with GPT-4cited by 2,579
  3. 2021Deep Reinforcement Learning at the Edge of the Statistical Precipicecited by 781
  4. 2019Neural Probabilistic Logic Programming in DeepProbLogcited by 389
  5. 2023Fast Segment Anythingcited by 286
  6. 2021MetaDrive: Composing Diverse Driving Scenarios for Generalizable Reinforcement Learningcited by 281
  7. 2018Programmatically Interpretable Reinforcement Learningcited by 192
  8. 2020SPACE: Unsupervised Object-Oriented Scene Representation via Spatial Attention and Decompositioncited by 190
  9. 2018Learning Equations for Extrapolation and Controlcited by 151
  10. 2022Decoupling Features in Hierarchical Propagation for Video Object Segmentationcited by 146
  11. 2017Visualizing and Understanding Atari Agentscited by 141
  12. 2020Distribution-Balanced Loss for Multi-Label Classification in Long-Tailed Datasetscited by 122
21 more
  1. 2016Extrapolation and learning equationscited by 106
  2. 2018SDRL: Interpretable and Data-efficient Deep Reinforcement Learning Leveraging Symbolic Planningcited by 77
  3. 2023Explaining black box text modules in natural language with language modelscited by 61
  4. 2022Improving Object-centric Learning with Query Optimizationcited by 60
  5. 2020Closed Loop Neural-Symbolic Learning via Integrating Neural Perception, Grammar Parsing, and Symbolic Reasoningcited by 58
  6. 2022Pre-Trained Image Encoder for Generalizable Visual Reinforcement Learningcited by 58
  7. 2023An Investigation into Pre-Training Object-Centric Representations for Reinforcement Learningcited by 49
  8. 2023Interpretable and Explainable Logical Policies via Neurally Guided Symbolic Abstractioncited by 45
  9. 2017Rationalization: A Neural Machine Translation Approach to Generating Natural Language Explanationscited by 37
  10. 2021Iterative Bounding MDPs: Learning Interpretable Policies via Non-Interpretable Methodscited by 31
  11. 2022A Survey of Explainable Reinforcement Learningcited by 31
  12. 2023OCAtari: Object-Centric Atari 2600 Reinforcement Learning Environmentscited by 30
  13. 2021Look Wide and Interpret Twice: Improving Performance on Interactive Instruction-following Taskscited by 25
  14. 2021Explainable Reinforcement Learning for Broad-XAI: A Conceptual Framework and Surveycited by 24
  15. 2024Interpretable Concept Bottlenecks to Align Reinforcement Learning Agentscited by 23
  16. 2022Boosting Object Representation Learning via Motion and Object Continuitycited by 17
  17. 2023Demystifying Embedding Spaces using Large Language Modelscited by 17
  18. 2022Neural-Symbolic Recursive Machine for Systematic Generalizationcited by 12
  19. 2022Symbolic Visual Reinforcement Learning: A Scalable Framework with Object-Level Abstraction and Differentiable Expression Searchcited by 9
  20. 2018Evolving simple programs for playing Atari gamescited by 8
  21. 2023Explaining Agent Behavior with Large Language Modelscited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 6; 2025: 4; 2026: 7.

17 papers.

Sort:

By area:

  1. 2024Interpretable and Editable Programmatic Tree Policies for Reinforcement Learningcited by 18
  2. 2024BlendRL: A Framework for Merging Symbolic and Neural Policy Learningcited by 14
  3. 2024HackAtari: Atari Learning Environments for Robust and Continual Reinforcement Learningcited by 11
  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. 2026MINT: Minimal Information Neuro-Symbolic Tree for Objective-Driven Knowledge-Gap Reasoning and Active Elicitationcited by 4
  7. 2025Evaluating Interpretable Reinforcement Learning by Distilling Policies into Programscited by 3
  8. 2025Better Decisions through the Right Causal World Modelcited by 3
  9. 2025Deep Reinforcement Learning via Object-Centric Attentioncited by 2
  10. 2025Neuro-Symbolic AI for Cybersecurity: State of the Art, Challenges, and Opportunitiescited by 2
  11. 2026REFLEX: Reflective Evolution from LLM Experiencecited by 1
  12. 2024Towards a Research Community in Interpretable Reinforcement Learning: the InterpPol Workshopcited by 0
5 more
  1. 2026Reinforcement Learning Enhancement Using Vector Semantic Representation and Symbolic Reasoning for Human-Centered Autonomous Emergency Brakingcited by 0
  2. 2026Boosting deep Reinforcement Learning using pretraining with Logical Optionscited by 0
  3. 2026GRAIL: Autonomous Concept Grounding for Neuro-Symbolic Reinforcement Learningcited by 0
  4. 2026Scheduling That Speaks: An Interpretable Programmatic Reinforcement Learning Frameworkcited by 0
  5. 2026ConceptTree: Bringing Semantic Transparency to Black-Box Decision Making for Robotic Manipulationcited by 0