One Decade of Universal Artificial Intelligence
Marcus Hutter RSCS @ ANU and SML @ NICTA Canberra, ACT, 0200, Australia、Department of Computer Science ETH Zürich, Switzerland
Abstract
The first decade of this century has seen the nascency of the first mathematical theory of general artificial intelligence. This theory of Universal Artificial Intelligence (UAI) has made significant contributions to many theoretical, philosophical, and practical AI questions. In a series of papers culminating in book (Hutter, 2005), an exciting sound and complete mathematical model for a super intelligent agent (AIXI) has been developed and rigorously analyzed. While nowadays most AI researchers avoid discussing intelligence, the award-winning PhD thesis (Legg, 2008) provided the philosophical embedding and investigated the UAI-based universal measure of rational intelligence, which is formal, objective and non-anthropocentric. Recently, effective approximations of AIXI have been derived and experimentally investigated in JAIR paper (Veness et al. 2011). This practical breakthrough has resulted in some impressive applications, finally muting earlier critique that UAI is only a theory. For the first time, without providing any domain knowledge, the same agent is able to self-adapt to a diverse range of interactive environments. For instance, AIXI is able to learn from scratch to pl
中文速览
人工通用智能（Artificial General Intelligence）长期缺乏严格的数学基础，研究者们甚至对"智能"本身的定义争论不休、莫衷一是。通用人工智能理论（Universal AI, UAI）以算法信息论和贝叶斯归纳推理为核心，构建了一个名为AIXI的最优理性智能体模型，从数学上严格定义了"什么是通用智能"，并给出了可量化的智能度量方式。理论层面，AIXI被证明是在所有可计算环境中期望累积奖励最大的智能体；实践层面，研究者已开发出AIXI的有效近似算法，使同一个智能体无需任何领域知识、仅凭试错就能自主学习玩转井字棋、吃豆人、扑克等多种游戏。这一工作之所以重要，在于它首次将通用智能从哲学概念转化为有坚实数学根基的可操作理论，为真正意义上的通用人工智能研究指明了一条既严谨又实用的道路。
原文 arXiv:1202.6153;中英对照 + 大白话阅读 https://aha.fim.ai/paper/1202.6153v1