环境中的物体可作为智能体的外部记忆，减少其内部存储需求。
Artifacts as Memory Beyond the Agent Boundary
- 用数学框架证明环境中的观察物（artifacts）能替代部分内部记忆
- 实验显示观察空间路径可显著降低学习所需记忆量
- 适合研究具身智能与认知外化机制的学者
具身认知观认为智能行为不仅依赖内部记忆，还取决于智能体对环境资源的主动利用。本文在强化学习框架下形式化这一观点，提出环境可作为智能体的记忆载体，并证明特定观测（称为artifacts）能减少历史状态的表征信息量。实验表明，当智能体观察空间路径时，学习高效策略所需的记忆量明显下降。该效应意外且隐式地产生于感官输入流中。研究还验证了该现象符合外部记忆的定性特征，为未来设计以环境为替代记忆的智能系统提供了理论基础。
原文摘要 · Abstract (English)
The situated view of cognition holds that intelligent behavior depends not only on internal memory, but on an agent's active use of environmental resources. Here, we begin formalizing this intuition within Reinforcement Learning (RL). We introduce a mathematical framing for how the environment can functionally serve as an agent's memory, and prove that certain observations, which we call artifacts, can reduce the information needed to represent history. We corroborate our theory with experiments showing that when agents observe spatial paths, the amount of memory required to learn a performant policy is reduced. Interestingly, this effect arises unintentionally, and implicitly through the agent's sensory stream. We discuss the implications of our findings, and show they satisfy qualitative properties previously used to ground accounts of external memory. Moving forward, we anticipate further work on this subject could reveal principled ways to exploit the environment as a substitute for explicit internal memory.
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。