arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1308.0702cs.AI
收藏

通用人工智能的普遍移情与伦理偏见

Universal Empathy and Ethical Bias for Artificial General Intelligence

AIDEUS;National Research University of Information Technology, Mechanics and Optics(国立信息技术、机械与光学大学);Aix Marseille Université(艾克斯-马赛大学);CNRS(法国国家科学研究中心)

Alexey Potapov, Sergey Rodionov

摘要:

理性代理通常是为了最大化回报而构建的。然而,AGI代理可以找到不受欢迎的方式来最大化任何先验奖励函数。因此,价值学习对于安全的AGI至关重要。我们假设世界的广义状态是有价值的-而不是奖励本身,并提出了AIXI的扩展,其中奖励仅用于引导分层值学习。修改后的AIXI代理被认为是在多代理环境中,其中其他代理可以是人类或其他“成熟”代理,这些值应该被“婴儿”AGI代理揭示和采用。作为通用智能模型的扩展,提出了设计这种具有道德偏见的移情代理的一般框架。此外,我们在简单的马尔可夫环境中进行了实验,证明了我们的方法在安全AGI中进行价值学习的可行性。

英文摘要:

Rational agents are usually built to maximize rewards. However, AGI agents can find undesirable ways of maximizing any prior reward function. Therefore value learning is crucial for safe AGI. We assume that generalized states of the world are valuable - not rewards themselves, and propose an extension of AIXI, in which rewards are used only to bootstrap hierarchical value learning. The modified AIXI agent is considered in the multi-agent environment, where other agents can be either humans or other "mature" agents, which values should be revealed and adopted by the "infant" AGI agent. General framework for designing such empathic agent with ethical bias is proposed also as an extension of the universal intelligence model. Moreover, we perform experiments in the simple Markov environment, which demonstrate feasibility of our approach to value learning in safe AGI.

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。

↑