梳理智能规划核心思想，打通AI各领域间的认知鸿沟。
AI Planning: A Primer and Survey (Preliminary Report)
- 以马尔可夫决策过程为框架，统一处理不确定与时间依赖的规划问题。
- 强调利用问题结构设计高效求解方法，提升计算效率与可扩展性。
- 适合对强化学习、推理系统或复杂决策建模感兴趣的科研人员阅读。
自动化决策是人工智能多个子领域（如强化学习、智能规划、基础模型、运筹学等）的核心议题。尽管近年有诸多尝试弥合这些领域间的差距，但仍存在大量未跨域传播的重要洞见。本文旨在简要介绍智能规划中经典且关键的思想，这些思想在其他领域中尚不广为人知。我们首先阐述经典的规划问题及其形式化表示，并通过马尔可夫决策过程框架拓展至处理不确定性和时间依赖性。随后，综述当前最先进的规划求解技术，重点分析其如何利用问题结构实现高效求解。最后，讨论智能规划中的若干前沿方向，包括从非结构化输入中学习规划结构，以及在未见场景中实现泛化的能力。
原文摘要 · Abstract (English)
Automated decision-making is a fundamental topic that spans multiple sub-disciplines in AI: reinforcement learning (RL), AI planning (AP), foundation models, and operations research, among others. Despite recent efforts to ``bridge the gaps'' between these communities, there remain many insights that have not yet transcended the boundaries. Our goal in this paper is to provide a brief and non-exhaustive primer on ideas well-known in AP, but less so in other sub-disciplines. We do so by introducing the classical AP problem and representation, and extensions that handle uncertainty and time through the Markov Decision Process formalism. Next, we survey state-of-the-art techniques and ideas for solving AP problems, focusing on their ability to exploit problem structure. Lastly, we cover subfields within AP for learning structure from unstructured inputs and learning to generalise to unseen scenarios and situations.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。