L. Bölöni

Autobiography based prediction in a situated AGI agent


Cite as:

L. Bölöni. Autobiography based prediction in a situated AGI agent. In Seventh Conf. of Artificial General Intelligence (AGI-2014), pp. 11–21, August 2014. Kurzweil Best AGI Idea Prize 2014

Download:

Download 

Abstract:

The ability to predict the unfolding of future events is an important feature of any situated AGI system. The most widely used approach is to create a \em model of the world, initialize it with the desired start state and use it to \em simulate possible future scenarios. In this paper we propose an alternative approach where there is no explicit model building involved. The agent memorizes its personal autobiography in an unprocessed narrative form. When a prediction is needed, the agent \em aligns story-lines from the autobiography with the current story, \em extends them into the future, then \em interprets them in the terms of the current events. We describe the implementation of this approach in the Xapagy cognitive architecture and present some experiments illustrating its operation.

BibTeX:

@inproceedings{Boloni-2014-AGI,
title = "Autobiography based prediction in a situated {AGI} agent",
author = "L. B{\"o}l{\"o}ni",
booktitle = "Seventh Conf. of Artificial General Intelligence (AGI-2014)",
year = "2014",
month = "August",
pages = "11-21",
note = "<b>Kurzweil Best AGI Idea Prize 2014</b>",
abstract = {
  The ability to predict the unfolding of future events is an important feature of any situated AGI system. The most widely used approach is to create a {\em model of the world}, initialize it with the desired start state and use it to {\em simulate} possible future scenarios. In this paper we propose an alternative approach where there is no explicit model building involved. The agent memorizes its personal autobiography in an unprocessed narrative form. When a prediction is needed, the agent {\em aligns} story-lines from the autobiography with the current story, {\em extends} them into the future, then {\em interprets} them in the terms of the current events. We describe the implementation of this approach in the Xapagy cognitive architecture and present some experiments illustrating its operation.
 },
}

Generated by bib2html.pl (written by Patrick Riley, Lotzi Boloni ) on Fri Jan 29, 2021 20:15:22