arXiv 2211.066652025-08-29cs.LGcs.AI

可解释强化学习综述：概念、算法与挑战

A Survey on Explainable Reinforcement Learning: Concepts, Algorithms, Challenges

College of Computer Science and Technology, Zhejiang University（浙江大学计算机科学与技术学院）；College of Computing and Data Science, Nanyang Technological University（南洋理工大学计算与数据科学学院）；School of Software Technology, Zhejiang University（浙江大学软件技术学院）；State Key Laboratory of Blockchain and Security, Zhejiang University（浙江大学区块链与安全国家重点实验室）

Yunpeng Qing, Shunyu Liu, Jie Song, Yang Zhou, Kaixuan Chen, Huiqiong Wang, Mingli Song

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文综述可解释强化学习XRL，提出涵盖模型、奖励、状态和任务解释的新分类，并关注人类知识增强的RL方法，总结挑战、机遇与开源资源。

摘要：

强化学习（Reinforcement Learning，RL）是一种流行的机器学习范式，其中智能体通过与环境交互来实现长期目标。在深度学习复兴的推动下，深度强化学习（Deep RL，DRL）已在一系列复杂控制任务中取得巨大成功。尽管取得了令人鼓舞的成果，但基于深度神经网络的主干网络被广泛视为黑箱，这使从业者难以在对安全性和可靠性要求极高的现实场景中信任并使用经过训练的智能体。为缓解这一问题，大量文献致力于通过构建内在可解释性或事后可解释性来揭示智能体的内部工作机制。在本综述中，我们全面回顾了关于可解释强化学习（eXplainable RL，XRL）的现有工作，并提出一种新的分类体系，将以往工作明确划分为模型解释、奖励解释、状态解释和任务解释方法。我们还回顾并强调了一类相反地利用人类知识来提升智能体学习效率与性能的RL方法，而这类方法在XRL领域常被忽视。文中讨论了XRL面临的若干挑战与机遇。本综述旨在对XRL进行高层次总结，并推动未来研究出更有效的XRL解决方案。相应的开源代码已在 https://github.com/Plankson/awesome-explainable-reinforcement-learning 收集并分类。

英文摘要：

Reinforcement Learning (RL) is a popular machine learning paradigm where intelligent agents interact with the environment to fulfill a long-term goal. Driven by the resurgence of deep learning, Deep RL (DRL) has witnessed great success over a wide spectrum of complex control tasks. Despite the encouraging results achieved, the deep neural network-based backbone is widely deemed as a black box that impedes practitioners to trust and employ trained agents in realistic scenarios where high security and reliability are essential. To alleviate this issue, a large volume of literature devoted to shedding light on the inner workings of the intelligent agents has been proposed, by constructing intrinsic interpretability or post-hoc explainability. In this survey, we provide a comprehensive review of existing works on eXplainable RL (XRL) and introduce a new taxonomy where prior works are clearly categorized into model-explaining, reward-explaining, state-explaining, and task-explaining methods. We also review and highlight RL methods that conversely leverage human knowledge to promote learning efficiency and performance of agents while this kind of method is often ignored in XRL field. Some challenges and opportunities in XRL are discussed. This survey intends to provide a high-level summarization of XRL and to motivate future research on more effective XRL solutions. Corresponding open source codes are collected and categorized at https://github.com/Plankson/awesome-explainable-reinforcement-learning.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。