Interpretable Reinforcement Learning With Neural Symbolic Logic

2021-01-01 · Zhihao Ma, Yuzheng Zhuang, Paul Weng, Dong Li, Kun Shao, Wulong Liu, Hankz Hankui Zhuo, Jianye Hao

Recent progress in deep reinforcement learning (DRL) can be largely attributed to the use of neural networks. However, this black-box approach fails to explain the learned policy in a human understandable way. To address this challenge and improve the transparency, we introduce symbolic logic into DRL and propose a Neural Symbolic Reinforcement Learning framework, in which states and actions are represented in an interpretable way using first-order logic. This framework features a relational reasoning module, which performs on task-level in Hierarchical Reinforcement Learning, enabling end-to-end learning with prior symbolic knowledge. Moreover, interpretability is enabled by extracting the logical rules learned by the reasoning module in a symbolic rule space, providing explainability on task level. Experimental results demonstrate better interpretability of subtasks, along with competing performance compared with existing approaches.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Deep Reinforcement LearningHierarchical Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)Relational Reasoning

Methods 이 논문이 사용한 방법론

Interpretability 설명 없음

Neuro-Symbolic Reinforcement Learning with First-Order Logic

2021-10-21 · EMNLP 2021 11 · Daiki Kimura, Masaki Ono, Subhajit Chaudhury, Ryosuke Kohita 외

Deep reinforcement learning (RL) methods often require many trials before convergence, and no direct interpretability of trained policies is provided. In order to achieve fast convergence and interpretability for the pol…

Deep Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)+1

Learning Symbolic Rules for Interpretable Deep Reinforcement Learning

2021-03-15 · Zhihao Ma, Yuzheng Zhuang, Paul Weng, Hankz Hankui Zhuo 외

Deep Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Three Pathways to Neurosymbolic Reinforcement Learning with Interpretable Model and Policy Networks

2024-02-07 · Peter Graf, Patrick Emami

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 simultaneous…

Deep Explainable Relational Reinforcement Learning: A Neuro-Symbolic Approach

2023-04-17 · Rishi Hazra, Luc De Raedt

Despite numerous successes in Deep Reinforcement Learning (DRL), the learned policies are not interpretable. Moreover, since DRL does not exploit symbolic relational representations, it has difficulties in coping with st…

Deep Reinforcement Learning reinforcement-learning Reinforcement Learning

Interpretable and Explainable Logical Policies via Neurally Guided Symbolic Abstraction

2023-06-02 · NeurIPS 2023 11

The limited priors required by neural networks make them the dominating choice to encode and learn policies using reinforcement learning (RL). However, they are also black-boxes, making it hard to understand the agent's …

Reinforcement Learning (RL)