The Disciple Integrated Shell and Methodology for Rapid Development of Knowledge-Based Agents
Abstract
The Disciple Learning Agent Shell (Disciple-LAS) is an integrated set of modules for rapid development of practical end-to-end knowledge-based agents, by domain experts, with limited assistance from knowledge engineers. DiscipleLAS and its associated agent building methodology are presented in (Tecuci et al. 1999). Therefore, in this paper, we introduce two very different agents developed with Disciple-LAS, to show its applicability to a wide range of domains. Then we introduce the different modules that are part of Disciple-LAS, and present their use in the agent building process. Finally we summarize the solutions proposed by the Disciple approach to some of the issues that have been found to be limiting factors in developing knowledge-based agents.
Cite
Text
Boicu et al. "The Disciple Integrated Shell and Methodology for Rapid Development of Knowledge-Based Agents." AAAI Conference on Artificial Intelligence, 1999.Markdown
[Boicu et al. "The Disciple Integrated Shell and Methodology for Rapid Development of Knowledge-Based Agents." AAAI Conference on Artificial Intelligence, 1999.](https://mlanthology.org/aaai/1999/boicu1999aaai-disciple/)BibTeX
@inproceedings{boicu1999aaai-disciple,
title = {{The Disciple Integrated Shell and Methodology for Rapid Development of Knowledge-Based Agents}},
author = {Boicu, Mihai and Wright, Kathryn and Marcu, Dorin and Lee, Seok Won and Bowman, Michael and Tecuci, Gheorghe},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {1999},
pages = {900-901},
url = {https://mlanthology.org/aaai/1999/boicu1999aaai-disciple/}
}