构建可持续学习、自主规划且结构可解释的智能体系统
Agential AI for Integrated Continual Learning, Deliberative Behavior, and Comprehensible Models
- 用组件变异与选择机制建模环境动态，保证学习完整性与最小性
- 结合规划算法在学习模型上生成高层行为模式，实现持续进化
- 适合需要长期适应与透明决策的复杂应用，如自动驾驶
当前机器学习范式在统计数据分析方面表现优异，解决了经典人工智能难以应对的问题。然而其存在关键缺陷：缺乏与规划的整合、内部结构难以理解、无法持续学习。本文提出初步设计的智能体型人工智能系统（Agential AI, AAI），原则上可独立运行或与统计方法协同工作，以克服上述问题。AAI 的核心是一种学习方法，通过组件级的变异与选择来建模时间动态，具备完备性、最小性和持续学习的保证。该方法与一个行为算法集成，后者基于学习到的模型进行规划，并封装高层次的行为模式。在简单环境中的初步实验表明，AAI 具有有效性与潜力。
原文摘要 · Abstract (English)
Contemporary machine learning paradigm excels in statistical data analysis, solving problems that classical AI couldn't. However, it faces key limitations, such as a lack of integration with planning, incomprehensible internal structure, and inability to learn continually. We present the initial design for an AI system, Agential AI (AAI), in principle operating independently or on top of statistical methods, designed to overcome these issues. AAI's core is a learning method that models temporal dynamics with guarantees of completeness, minimality, and continual learning, using component-level variation and selection to learn the structure of the environment. It integrates this with a behavior algorithm that plans on a learned model and encapsulates high-level behavior patterns. Preliminary experiments on a simple environment show AAI's effectiveness and potential.
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。