系统梳理强化学习中状态表示学习的主流方法与评估标准。
A Survey of State Representation Learning for Deep Reinforcement Learning
- 按机制分为六类，分析各自优劣与适用场景。
- 提出评估表示质量的通用框架，提升可比性。
- 适合刚入强化学习领域的研究者快速入门。
表示学习方法是应对序列决策问题中复杂观测空间的重要工具。近年来，众多方法采用多样化策略在强化学习中学习有意义的状态表示，从而提升样本效率、泛化能力与性能表现。本综述旨在在无模型在线设置下对这些方法进行广泛分类，探讨其在状态表示学习上的不同策略。我们将方法归为六大类别，详述其机制、优势与局限性。通过这一分类体系，旨在深化对该领域的理解，并为新研究者提供指引。同时讨论了表示质量的评估技术，并指出相关未来方向。
原文摘要 · Abstract (English)
Representation learning methods are an important tool for addressing the challenges posed by complex observations spaces in sequential decision making problems. Recently, many methods have used a wide variety of types of approaches for learning meaningful state representations in reinforcement learning, allowing better sample efficiency, generalization, and performance. This survey aims to provide a broad categorization of these methods within a model-free online setting, exploring how they tackle the learning of state representations differently. We categorize the methods into six main classes, detailing their mechanisms, benefits, and limitations. Through this taxonomy, our aim is to enhance the understanding of this field and provide a guide for new researchers. We also discuss techniques for assessing the quality of representations, and detail relevant future directions.
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。