arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2112.06336cs.AIcs.LG
收藏

将知识表示为预测(以及将状态表示为知识)

Representing Knowledge as Predictions (and State as Knowledge)

Mark Ring

摘要:

本文展示了如何一个单一的机制允许知识直接从代理的原始感觉运动流逐层构建。这种机制,一般价值函数(GVF)或“预测”,捕捉高级,抽象的知识作为一组预测现有的功能和知识,完全基于代理的低层次的感觉和行动。因此,预测提供了一种将原始感觉运动数据组织成无限层数的有用抽象的表示-这是人工智能和认知科学长期追求的目标。本文的核心是一个详细的思想实验,提供了一个具体的,一步一步的正式说明人工代理如何建立真正的,有用的,抽象的知识,从其原始的感觉运动经验。知识表示为一组分层的预测(预报)的代理人的观察到的后果,其行动。这幅图显示了12个独立的层:最低层由原始像素、触摸和力传感器以及少量动作组成;较高的层在抽象中增加,最终产生了关于智能体世界的丰富知识,大致对应于门口、墙壁、房间和平面图。然后,我认为,这种一般的机制可能允许广泛的日常人类知识的代表。

英文摘要:

This paper shows how a single mechanism allows knowledge to be constructed layer by layer directly from an agent's raw sensorimotor stream. This mechanism, the General Value Function (GVF) or "forecast," captures high-level, abstract knowledge as a set of predictions about existing features and knowledge, based exclusively on the agent's low-level senses and actions. Thus, forecasts provide a representation for organizing raw sensorimotor data into useful abstractions over an unlimited number of layers--a long-sought goal of AI and cognitive science. The heart of this paper is a detailed thought experiment providing a concrete, step-by-step formal illustration of how an artificial agent can build true, useful, abstract knowledge from its raw sensorimotor experience alone. The knowledge is represented as a set of layered predictions (forecasts) about the agent's observed consequences of its actions. This illustration shows twelve separate layers: the lowest consisting of raw pixels, touch and force sensors, and a small number of actions; the higher layers increasing in abstraction, eventually resulting in rich knowledge about the agent's world, corresponding roughly to doorways, walls, rooms, and floor plans. I then argue that this general mechanism may allow the representation of a broad spectrum of everyday human knowledge.

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。

↑