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 1411.1373cs.AI
收藏

伦理人工智能

Ethical Artificial Intelligence

Machine Intelligence Research Institute(机器智能研究院)

Bill Hibbard

摘要:

这本书长的文章结合了几篇同行评议的论文和新材料,分析了伦理人工智能(AI)的问题。未来人工智能系统的行为可以通过数学方程来描述,这些方程适用于分析可能的非预期人工智能行为以及人工智能设计可以避免它们的方式。这篇文章提出了效用最大化代理和避免代理定义中的无限集的案例。它展示了如何使用基于模型的效用函数来避免智能体自我欺骗,以及如何使用效用函数来避免智能体破坏其奖励生成器(有时称为“反常实例化”),该效用函数从人类在不同时间点的角度评估在一个时间点的结果。它认为,智能体可以通过准确地学习人类价值观来避免无意的工具性行为(有时称为“基本人工智能驱动”或“工具性目标”)。本文定义了一个自建模代理框架,并展示了它如何避免资源限制的问题,被其他代理预测,以及代理的效用函数与其定义之间的不一致(这个问题的一个版本有时被称为“动机价值选择”)。本文还讨论了未来的人工智能将如何与当前的人工智能不同,人工智能的政治,以及人工智能的最终用途,以帮助理解宇宙的性质和我们在其中的位置。

英文摘要:

This book-length article combines several peer reviewed papers and new material to analyze the issues of ethical artificial intelligence (AI). The behavior of future AI systems can be described by mathematical equations, which are adapted to analyze possible unintended AI behaviors and ways that AI designs can avoid them. This article makes the case for utility-maximizing agents and for avoiding infinite sets in agent definitions. It shows how to avoid agent self-delusion using model-based utility functions and how to avoid agents that corrupt their reward generators (sometimes called "perverse instantiation") using utility functions that evaluate outcomes at one point in time from the perspective of humans at a different point in time. It argues that agents can avoid unintended instrumental actions (sometimes called "basic AI drives" or "instrumental goals") by accurately learning human values. This article defines a self-modeling agent framework and shows how it can avoid problems of resource limits, being predicted by other agents, and inconsistency between the agent's utility function and its definition (one version of this problem is sometimes called "motivated value selection"). This article also discusses how future AI will differ from current AI, the politics of AI, and the ultimate use of AI to help understand the nature of the universe and our place in it.

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。

↑