ML Anthology

PLOW: A Collaborative Task Learning Agent

James F. Allen, Nathanael Chambers, George Ferguson, Lucian Galescu, Hyuckchul Jung, Mary D. Swift, William Taysom
AAAI 2007 pp. 1514-1519
/aaai/2007/allen2007aaai-plow/

Abstract

To be effective, an agent that collaborates with humans needs to be able to learn new tasks from humans they work with. This paper describes a system that learns executable task models from a single collaborative learning session consisting of demonstration, explanation and dialogue. To accomplish this, the system integrates a range of AI technologies: deep natural language understanding, knowledge representation and reasoning, dialogue systems, planning/agent-based systems and machine learning. A formal evaluation shows the approach has great promise.

PDF AAAI Semantic Scholar

Cite

Text

Allen et al. "PLOW: A Collaborative Task Learning Agent." AAAI Conference on Artificial Intelligence, 2007.

Markdown

[Allen et al. "PLOW: A Collaborative Task Learning Agent." AAAI Conference on Artificial Intelligence, 2007.](https://mlanthology.org/aaai/2007/allen2007aaai-plow/)

BibTeX

@inproceedings{allen2007aaai-plow,
  title     = {{PLOW: A Collaborative Task Learning Agent}},
  author    = {Allen, James F. and Chambers, Nathanael and Ferguson, George and Galescu, Lucian and Jung, Hyuckchul and Swift, Mary D. and Taysom, William},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2007},
  pages     = {1514-1519},
  url       = {https://mlanthology.org/aaai/2007/allen2007aaai-plow/}
}