arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1606.04250cs.AI
收藏

自主智能体信息整合的实验与因果观

Experimental and causal view on information integration in autonomous agents

Max Planck Institute for Intelligent Systems(马克斯·普朗克智能系统研究所);Microsoft Research Cambridge(微软剑桥研究院)

Philipp Geiger, Katja Hofmann, Bernhard Schölkopf

摘要:

关于世界的数字化可用但异构的信息量是显着的,和新技术,如自动驾驶汽车,灵巧家庭,或物联网可能会进一步增加it.In本文中,我们提出了初步的想法如何利用这种异构信息的问题的某些方面的自主智能体。在讨论了一些现有方法的潜力和局限性后,我们研究了\emph{experiments}如何帮助更好地理解这个问题。具体来说,我们提出了一个简单的代理,从不同的代理集成视频数据,并实现和评估它的新的实验平台\emph{Malmo}的版本。第二个调查的重点是如何不同的代理,代理的感官数据,和\emph{causal}信息的硬件信息可以被用于代理之间的知识转移,随后更有效的数据决策。最后,我们讨论了未来可能采取的步骤。理论和实验,并制定开放的问题。

英文摘要:

The amount of digitally available but heterogeneous information about the world is remarkable, and new technologies such as self-driving cars, smart homes, or the internet of things may further increase it. In this paper we present preliminary ideas about certain aspects of the problem of how such heterogeneous information can be harnessed by autonomous agents. After discussing potentials and limitations of some existing approaches, we investigate how \emph{experiments} can help to obtain a better understanding of the problem. Specifically, we present a simple agent that integrates video data from a different agent, and implement and evaluate a version of it on the novel experimentation platform \emph{Malmo}. The focus of a second investigation is on how information about the hardware of different agents, the agents' sensory data, and \emph{causal} information can be utilized for knowledge transfer between agents and subsequently more data-efficient decision making. Finally, we discuss potential future steps w.r.t.\ theory and experimentation, and formulate open questions.

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。

↑