Modular self-organization for a long-living autonomous agent
Proceedings of the Eighteenth International Joint Conference on Artificial Intelligence. Pages 1440-1441.
Abstract
The aim of this paper is to provide a sound framework for addressing a difficult problem: the automatic construction of an autonomous agent's modular architecture. We briefly present two apparently uncorrelated frameworks: Autonomous planning through Markov Decision Processes and Kernel Clustering. Our fundamental idea is that the former addresses autonomy whereas the latter allows to tackle self-organizing issues. Relying on both frameworks, we show that modular selforganization can be formalized as a clustering problem in the space of MDPs . We derive a modular self-organizing algorithm in which an autonomous agent learns to efficiently spread n planning problems over m initially blank modules with m < n.
@inproceedings{ijcai2003p229,
title = {Modular self-organization for a long-living autonomous agent},
author = {Scherrer, Bruno},
booktitle = {Proceedings of the Eighteenth International Joint Conference on
Artificial Intelligence, {IJCAI-03}},
publisher = {International Joint Conferences on Artificial Intelligence},
editor = {Georg Gottlob},
pages = {1440--1441},
year = {2003},
url = {https://ijcai.org/proceedings/2003/229},
}
TY - CPAPER TI - Modular self-organization for a long-living autonomous agent AU - Scherrer, Bruno T2 - Proceedings of the Eighteenth International Joint Conference on Artificial Intelligence, IJCAI-03 PB - International Joint Conferences on Artificial Intelligence PY - 2003 SP - 1440 EP - 1441 UR - https://ijcai.org/proceedings/2003/229 ER -Copied
Machine-readable versions of this paper, for tools and AI agents:
