Three Pathways To Neurosymbolic Reinforcement Learning With Interpretable Model And Policy Networks
2024 · Peter Graf, Patrick Emami
Abstract
Neurosymbolic AI combines the interpretability, parsimony, and explicit reasoning of classical symbolic approaches with the statistical learning of data-driven neural approaches. Models and policies that are simultaneously differentiable and interpretable may be key enablers of this marriage. This paper demonstrates three pathways to implementing such models and policies in a real-world reinforcement learning setting. Specifically, we study a broad class of neural networks that build interpretable semantics directly into their architecture. We reveal and highlight both the potential and the essential difficulties of combining logic, simulation, and learning. One lesson is that learning benefits from continuity and differentiability, but classical logic is discrete and non-differentiable. The relaxation to real-valued, differentiable representations presents a trade-off; the more learnable, the less interpretable. Another lesson is that using logic in the context of a numerical simulati
Authors
(none)
Tags
Stats
Related papers
- S-REINFORCE: A Neuro-symbolic Policy Gradient Approach For Interpretable Reinforcement Learning (2023)0.00
- End-to-end Neuro-symbolic Reinforcement Learning With Textual Explanations (2024)0.00
- Blendrl: A Framework For Merging Symbolic And Neural Policy Learning (2024)0.00
- Evaluating Interpretable Reinforcement Learning By Distilling Policies Into Programs (2025)0.00
- "so, Tell Me About Your Policy...": Distillation Of Interpretable Policies From Deep Reinforcement Learning Agents (2025)0.00
- Interpretable End-to-end Neurosymbolic Reinforcement Learning Agents (2024)0.00
- Interpretable Model-based Hierarchical Reinforcement Learning Using Inductive Logic Programming (2021)0.00
- From Explainability To Interpretability: Interpretable Policies In Reinforcement Learning Via Model Explanation (2025)0.00