Group-Aware Coordination Graph for Multi-Agent Reinforcement Learning
Abstract
The proportional veto principle, which captures the idea that a candidate vetoed by a large group of voters should not be chosen, has been studied for ranked ballots in single-winner voting. We introduce a version of this principle for approval ballots, which we call flexible-voter representation (FVR). We show that while the approval voting rule and other natural scoring rules provide the optimal FVR guarantee only for some flexibility threshold, there exists a scoring rule that is FVR-optimal for all thresholds simultaneously. We also extend our results to multi-winner voting.
Cite
Text
Duan et al. "Group-Aware Coordination Graph for Multi-Agent Reinforcement Learning." International Joint Conference on Artificial Intelligence, 2024. doi:10.24963/ijcai.2024/434Markdown
[Duan et al. "Group-Aware Coordination Graph for Multi-Agent Reinforcement Learning." International Joint Conference on Artificial Intelligence, 2024.](https://mlanthology.org/ijcai/2024/duan2024ijcai-group/) doi:10.24963/ijcai.2024/434BibTeX
@inproceedings{duan2024ijcai-group,
title = {{Group-Aware Coordination Graph for Multi-Agent Reinforcement Learning}},
author = {Duan, Wei and Lu, Jie and Xuan, Junyu},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {2024},
pages = {3926-3934},
doi = {10.24963/ijcai.2024/434},
url = {https://mlanthology.org/ijcai/2024/duan2024ijcai-group/}
}