Improving Multi-Agent Coordination by Learning to Estimate Contention
Abstract
We present a multi-agent learning algorithm, ALMA-Learning, for efficient and fair allocations in large-scale systems. We circumvent the traditional pitfalls of multi-agent learning (e.g., the moving target problem, the curse of dimensionality, or the need for mutually consistent actions) by relying on the ALMA heuristic as a coordination mechanism for each stage game. ALMA-Learning is decentralized, observes only own action/reward pairs, requires no inter-agent communication, and achieves near-optimal (<5% loss) and fair coordination in a variety of synthetic scenarios and a real-world meeting scheduling problem. The lightweight nature and fast learning constitute ALMA-Learning ideal for on-device deployment.
Cite
Text
Danassis et al. "Improving Multi-Agent Coordination by Learning to Estimate Contention." International Joint Conference on Artificial Intelligence, 2021. doi:10.24963/IJCAI.2021/18Markdown
[Danassis et al. "Improving Multi-Agent Coordination by Learning to Estimate Contention." International Joint Conference on Artificial Intelligence, 2021.](https://mlanthology.org/ijcai/2021/danassis2021ijcai-improving/) doi:10.24963/IJCAI.2021/18BibTeX
@inproceedings{danassis2021ijcai-improving,
title = {{Improving Multi-Agent Coordination by Learning to Estimate Contention}},
author = {Danassis, Panayiotis and Wiedemair, Florian and Faltings, Boi},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {2021},
pages = {125-131},
doi = {10.24963/IJCAI.2021/18},
url = {https://mlanthology.org/ijcai/2021/danassis2021ijcai-improving/}
}