BriefGPT.xyz
Jun, 2023
通过神经引导的符号抽象获得可解释的逻辑策略
Interpretable and Explainable Logical Policies via Neurally Guided Symbolic Abstraction
HTML
PDF
Quentin Delfosse, Hikaru Shindo, Devendra Dhami, Kristian Kersting
TL;DR
研究介绍了一种基于神经网络和可微逻辑的方法，旨在同时实现可解释性和解释性，引入了物理引导的可微分逻辑策略，评估表明其在识别可解释的策略方面比仅使用神经策略更加优越。
Abstract
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
→