Neurosymbolic Reinforcement Learning and Planning: A Survey
Neurosymbolic Reinforcement Learning and Planning: A Survey
复制标题
DOI：
10.1109/tai.2023.3311428
复制
发表时间：
2023-09
期刊：
影响因子：
--
通讯作者：
Kamal Acharya;Waleed Raza;Carlos Dourado;Alvaro Velasquez;Houbing Song
中科院分区：
文献类型：
--
作者：
Kamal Acharya;Waleed Raza;Carlos Dourado;Alvaro Velasquez;Houbing Song
神经成像人工智能的领域（神经符号AI）正在迅速发展，并且已经成为一个流行的研究主题，包括神经符号深度学习和神经符号的增强型（神经符号RL）与传统的学习方法相比，透明度和透明度（Simparive and and and）。长期以来，人工智能（AI）的概念是使用奖励和惩罚模仿人类行为，是神经质rl的基本组成部分，这两个领域的整合已经产生了本文的目的，这是通过对我们的评估群体进行的，这是有助于神经肌的新兴领域。我们基于RL中的神经和象征性部分的作用，分为三种分类：出于理由，学习的理由和学习，这些类别进一步分为子类别。此动态字段中的应用。
The area of neurosymbolic artificial intelligence (Neurosymbolic AI) is rapidly developing and has become a popular research topic, encompassing subfields, such as neurosymbolic deep learning and neurosymbolic reinforcement learning (Neurosymbolic RL). Compared with traditional learning methods, Neurosymbolic AI offers significant advantages by simplifying complexity and providing transparency and explainability. Reinforcement learning (RL), a long-standing artificial intelligence (AI) concept that mimics human behavior using rewards and punishment, is a fundamental component of Neurosymbolic RL, a recent integration of the two fields that has yielded promising results. The aim of this article is to contribute to the emerging field of Neurosymbolic RL by conducting a literature survey. Our evaluation focuses on the three components that constitute Neurosymbolic RL: neural, symbolic, and RL. We categorize works based on the role played by the neural and symbolic parts in RL, into three taxonomies: learning for reasoning, reasoning for learning, and learning–reasoning. These categories are further divided into subcategories based on their applications. Furthermore, we analyze the RL components of each research work, including the state space, action space, policy module, and RL algorithm. In addition, we identify research opportunities and challenges in various applications within this dynamic field.