Optimising Spatial Teamwork Under Uncertainty
Abstract
We introduce a novel method for assessing agent teamwork based on their spatial coordination. Our approach models the influence of spatial proximity on team formation and sustained spatial dominance over adversaries using a Multi-agent Markov Decision Process. We develop an algorithm to derive efficient teamwork strategies by combining Monte Carlo Tree Search and linear programming. When applied to team defence in football (soccer) using real-world data, our approach reduces opponent threat by 21%, outperforming optimised individual behaviour by 6%. Additionally, our model enhances the predictive accuracy of future attack locations and provides deeper insights compared to existing teamwork models that do not explicitly consider the spatial dynamics of teamwork.
Cite
Text
Everett et al. "Optimising Spatial Teamwork Under Uncertainty." AAAI Conference on Artificial Intelligence, 2025. doi:10.1609/AAAI.V39I22.34482Markdown
[Everett et al. "Optimising Spatial Teamwork Under Uncertainty." AAAI Conference on Artificial Intelligence, 2025.](https://mlanthology.org/aaai/2025/everett2025aaai-optimising/) doi:10.1609/AAAI.V39I22.34482BibTeX
@inproceedings{everett2025aaai-optimising,
title = {{Optimising Spatial Teamwork Under Uncertainty}},
author = {Everett, Gregory and Beal, Ryan J. and Matthews, Tim and Norman, Timothy J. and Ramchurn, Sarvapali D.},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {2025},
pages = {23168-23176},
doi = {10.1609/AAAI.V39I22.34482},
url = {https://mlanthology.org/aaai/2025/everett2025aaai-optimising/}
}