End-to-end Neuro-symbolic Reinforcement Learning With Textual Explanations

Abstract

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

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyluo2024end

Related papers

• Three Pathways To Neurosymbolic Reinforcement Learning With Interpretable Model And Policy Networks (2024)0.00
• Generation Of Policy-level Explanations For Reinforcement Learning (2019)11.39
• S-REINFORCE: A Neuro-symbolic Policy Gradient Approach For Interpretable Reinforcement Learning (2023)0.00
• Interpretable End-to-end Neurosymbolic Reinforcement Learning Agents (2024)0.00
• Experiential Explanations For Reinforcement Learning (2022)2.26
• From Explainability To Interpretability: Interpretable Policies In Reinforcement Learning Via Model Explanation (2025)0.00
• Generating Explanations From Deep Reinforcement Learning Using Episodic Memory (2022)0.00
• Blendrl: A Framework For Merging Symbolic And Neural Policy Learning (2024)0.00