Toward a Model of Intelligence as an Economy of Agents
Abstract
A market-based algorithm is presented which autonomously apportions complex tasks to multiple cooperating agents giving each agent the motivation of improving performance of the whole system. A specific model, called “The Hayek Machine” is proposed and tested on a simulated Blocks World (BW) planning problem. Hayek learns to solve more complex BW problems than any previous learning algorithm. Given intermediate reward and simple features, it has learned to efficiently solve arbitrary BW problems. The Hayek Machine can also be seen as a model of evolutionary economics.
Cite
Text
Baum. "Toward a Model of Intelligence as an Economy of Agents." Machine Learning, 1999. doi:10.1023/A:1007593124513Markdown
[Baum. "Toward a Model of Intelligence as an Economy of Agents." Machine Learning, 1999.](https://mlanthology.org/mlj/1999/baum1999mlj-model/) doi:10.1023/A:1007593124513BibTeX
@article{baum1999mlj-model,
title = {{Toward a Model of Intelligence as an Economy of Agents}},
author = {Baum, Eric B.},
journal = {Machine Learning},
year = {1999},
pages = {155-185},
doi = {10.1023/A:1007593124513},
volume = {35},
url = {https://mlanthology.org/mlj/1999/baum1999mlj-model/}
}