Counterfactual Policy Evaluation for Improving Coordination Quality in Multi-Agent Reinforcement Systems
American Journal Of Big Data · 01.04.2026 · 7 (1) · 293-301
DOI: 10.71465/ajbd3668 ↗Kurz gefasst
Fachartikel in der Zeitschrift American Journal Of Big Data, online erschienen am 01.04.2026. Verfasst von Jisoo Kim und 2 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Observed performance in collaborative decision systems often fails to reveal the true contribution of individual actions due to interaction dependencies. This study develops a counterfactual policy evaluation framework to better quantify action-level impact in multi-agent settings. The approach integrates doubly robust estimation with reinforcement learning to evaluate alternative decision trajectories without additional environment interaction. Experiments are conducted on 8,900 coordination tasks with varying interaction complexity. The proposed method improves policy evaluation accuracy by 26.1% and leads to a 19.4% increase in downstream policy performance when used for policy refinement. Moreover, coordination conflicts decrease by 23.7%, indicating more consistent collective behavior. These findings highlight the value of counterfactual reasoning in optimizing collaborative policies.
Zitieren
APA
Kim, J., Park, M., & Lee, H. (2026). Counterfactual Policy Evaluation for Improving Coordination Quality in Multi-Agent Reinforcement Systems. American Journal Of Big Data, 7(1), 293-301. https://doi.org/10.71465/ajbd3668
Vancouver
Kim J, Park M, Lee H. Counterfactual Policy Evaluation for Improving Coordination Quality in Multi-Agent Reinforcement Systems. American Journal Of Big Data. 2026;7(1):293-301. doi:10.71465/ajbd3668
BibTeX
@article{Kim2026,
author = {Kim, Jisoo and Park, Minho and Lee, Hyunwoo},
title = {Counterfactual Policy Evaluation for Improving Coordination Quality in Multi-Agent Reinforcement Systems},
journal = {American Journal Of Big Data},
year = {2026},
volume = {7},
number = {1},
pages = {293--301},
doi = {10.71465/ajbd3668}
}
EUVIMED