Goal-Driven Learning in the GILA Integrated Intelligence Architecture
Proceedings of the Twenty-First International Joint Conference on Artificial Intelligence. Pages 1205-1209.
Abstract
Goal Driven Learning (GDL) focuses on systems that determine by themselves what has to be learnt and how to learn it. Typically GDL systems use meta-reasoning capabilities over a base {em reasoner}, identifying learning goals and devising strategies. In this paper we present a novel GDL technique to deal with complex AI systems where the meta-reasoning module has to analyze the reasoning trace of multiple components with potentially different learning paradigms. Our approach works by distributing the generation of learning strategies among the different modules instead of centralizing it in the meta-reasoner. We implemented our technique in the GILA system, that works in the airspace task orders domain, showing an increase in performance.Jainarayan Radhakrishnan, Santiago Ontanon, Ashwin Ram
@inproceedings{ijcai2009p203,
title = {Goal-Driven Learning in the GILA Integrated Intelligence Architecture},
author = {Radhakrishnan, Jainarayan and Ontañón, Santiago and Ram, Ashwin},
booktitle = {Proceedings of the Twenty-First International Joint Conference on
Artificial Intelligence, {IJCAI-09}},
publisher = {International Joint Conferences on Artificial Intelligence},
editor = {Hiroaki Kitano},
pages = {1205--1209},
year = {2009},
url = {https://ijcai.org/proceedings/2009/203},
}
TY - CPAPER TI - Goal-Driven Learning in the GILA Integrated Intelligence Architecture AU - Radhakrishnan, Jainarayan AU - Ontañón, Santiago AU - Ram, Ashwin T2 - Proceedings of the Twenty-First International Joint Conference on Artificial Intelligence, IJCAI-09 PB - International Joint Conferences on Artificial Intelligence PY - 2009 SP - 1205 EP - 1209 UR - https://ijcai.org/proceedings/2009/203 ER -Copied
Machine-readable versions of this paper, for tools and AI agents:
