发帖
雷达卡
摘要翻译：
我假定人类或其他智能体的功能或应该功能如下。它们储存所有的感官观察--这些数据是神圣的。在任何时候，给定某些agent当前的编码能力，部分数据可以通过一个简短且希望快速的程序/描述/解释/世界模型进行压缩。在代理人的主观眼中，这样的数据比其他数据更有规律，也更“漂亮”。众所周知，规则性和可重复性的知识可以提高Agent计划行动的能力，从而获得外部奖励。然而，如果没有这样的奖励，已知的美丽是乏味的。然后“趣味性”成为主观美的一阶导数：随着学习agent改进其压缩算法，以前表面上随机的数据部分在主观上变得更加规则和美丽。这种可压缩性的进步是由好奇心驱动来衡量和最大化的：创建扩展观察历史的动作序列，并产生以前未知/不可预测但可快速学习的算法规则。通过将被动无监督学习扩展到主动数据选择的情况，我们讨论了如何在计算机上自然地实现上述所有内容：我们奖励一个普通的强化学习器（可以访问自适应压缩器），因为它的行为改善了不断增长的数据的主观压缩性。在可压缩性方面的一个异常大的突破值得称为“发现”。艺术家、舞蹈家、音乐家、纯粹数学家的“创造力”可以被视为这一原则的副产品。几个定性的例子支持这一假设。
---
英文标题：
《Simple Algorithmic Principles of Discovery, Subjective Beauty, Selective
Attention, Curiosity & Creativity》
---
作者：
Juergen Schmidhuber
---
最新提交年份：
2007
---
分类信息：
一级分类：Computer Science 计算机科学
二级分类：Artificial Intelligence 人工智能
分类描述：Covers all areas of AI except Vision, Robotics, Machine Learning, Multiagent Systems, and Computation and Language (Natural Language Processing), which have separate subject areas. In particular, includes Expert Systems, Theorem Proving (although this may overlap with Logic in Computer Science), Knowledge Representation, Planning, and Uncertainty in AI. Roughly includes material in ACM Subject Classes I.2.0, I.2.1, I.2.3, I.2.4, I.2.8, and I.2.11.
涵盖了人工智能的所有领域，除了视觉、机器人、机器学习、多智能体系统以及计算和语言（自然语言处理），这些领域有独立的学科领域。特别地，包括专家系统，定理证明（尽管这可能与计算机科学中的逻辑重叠），知识表示，规划，和人工智能中的不确定性。大致包括ACM学科类I.2.0、I.2.1、I.2.3、I.2.4、I.2.8和I.2.11中的材料。
--
一级分类：Computer Science 计算机科学
二级分类：Graphics 图形学
分类描述：Covers all aspects of computer graphics. Roughly includes material in all of ACM Subject Class I.3, except that I.3.5 is is likely to have Computational Geometry as the primary subject area.
涵盖了计算机图形学的各个方面。大致包括所有ACM课程I.3的材料，除了I.3.5可能有计算几何作为主要的学科领域。
--
---
英文摘要：
I postulate that human or other intelligent agents function or should function as follows. They store all sensory observations as they come - the data is holy. At any time, given some agent's current coding capabilities, part of the data is compressible by a short and hopefully fast program / description / explanation / world model. In the agent's subjective eyes, such data is more regular and more "beautiful" than other data. It is well-known that knowledge of regularity and repeatability may improve the agent's ability to plan actions leading to external rewards. In absence of such rewards, however, known beauty is boring. Then "interestingness" becomes the first derivative of subjective beauty: as the learning agent improves its compression algorithm, formerly apparently random data parts become subjectively more regular and beautiful. Such progress in compressibility is measured and maximized by the curiosity drive: create action sequences that extend the observation history and yield previously unknown / unpredictable but quickly learnable algorithmic regularity. We discuss how all of the above can be naturally implemented on computers, through an extension of passive unsupervised learning to the case of active data selection: we reward a general reinforcement learner (with access to the adaptive compressor) for actions that improve the subjective compressibility of the growing data. An unusually large breakthrough in compressibility deserves the name "discovery". The "creativity" of artists, dancers, musicians, pure mathematicians can be viewed as a by-product of this principle. Several qualitative examples support this hypothesis.
---
PDF链接：
https://arxiv.org/pdf/0709.0674
京公网安备 11010802022788号
