Learning Procedural Knowledge to Better Coordinate
Abstract
A fundamental difficulty faced by groups of agents that work together is how to efficiently coordinate their efforts. This paper presents techniques that allow heterogeneous agents to more efficiently solve coordination problems by acquiring procedural knowledge. In particular, each agent autonomously learns coordinated procedures that reflect her contributions towards successful past joint behavior. Empirical results validate the significant benefits of coordinated procedures. 1
Cite
Text
Garland and Alterman. "Learning Procedural Knowledge to Better Coordinate." International Joint Conference on Artificial Intelligence, 2001.Markdown
[Garland and Alterman. "Learning Procedural Knowledge to Better Coordinate." International Joint Conference on Artificial Intelligence, 2001.](https://mlanthology.org/ijcai/2001/garland2001ijcai-learning/)BibTeX
@inproceedings{garland2001ijcai-learning,
title = {{Learning Procedural Knowledge to Better Coordinate}},
author = {Garland, Andrew and Alterman, Richard},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {2001},
pages = {1073-1083},
url = {https://mlanthology.org/ijcai/2001/garland2001ijcai-learning/}
}