Predicting and Preventing Coordination Problems in Cooperative Q-Learning Systems
Abstract
We present a conceptual framework for creating Q-learning-based algorithms that converge to optimal equilibria in cooperative multiagent settings. This framework includes a set of conditions that are sufficient to guarantee optimal system performance. We demonstrate the efficacy of the framework by using it to analyze several well-known multi-agent learning algorithms and conclude by employing it as a design tool to construct a simple, novel multiagent learning algorithm.
Cite
Text
Fulda and Ventura. "Predicting and Preventing Coordination Problems in Cooperative Q-Learning Systems." International Joint Conference on Artificial Intelligence, 2007.Markdown
[Fulda and Ventura. "Predicting and Preventing Coordination Problems in Cooperative Q-Learning Systems." International Joint Conference on Artificial Intelligence, 2007.](https://mlanthology.org/ijcai/2007/fulda2007ijcai-predicting/)BibTeX
@inproceedings{fulda2007ijcai-predicting,
title = {{Predicting and Preventing Coordination Problems in Cooperative Q-Learning Systems}},
author = {Fulda, Nancy and Ventura, Dan},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {2007},
pages = {780-785},
url = {https://mlanthology.org/ijcai/2007/fulda2007ijcai-predicting/}
}