Reinforcement learning with reputation-based adaptive exploration promotes cooperation
Chaos: An Interdisciplinary Journal of Nonlinear Science · 01.08.2026 · 36 (8)
DOI: 10.1063/5.0348706 ↗Kurz gefasst
Fachartikel in der Zeitschrift Chaos: An Interdisciplinary Journal of Nonlinear Science, online erschienen am 07.08.2026. Verfasst von An Li und 7 weiteren Autor:innen. Beteiligte Einrichtung: School of Mathematical Sciences, Beihang University, Beijing 100191, China. Hauptthemen laut MEDLINE: Cooperative Behavior. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 79 Literaturangaben. Gefördert von: National Science and Technology Major Project, National Natural Science Foundation of China, Fundamental Research Funds for the Central Universities.
Abstract (Originalsprache)
Reinforcement learning provides a framework for studying how individuals adjust their behavior through repeated interaction and feedback in social dilemmas. In Q-learning, exploration controls how often agents choose actions other than those favored by their current learned Q-values. Yet, the existing models usually treat the exploration rate as a constant parameter. In systems with social evaluation, however, trial-and-error behavior carries different costs and opportunities for agents with different reputations, making exploration dependent on social standing rather than uniform across agents. Herein, we develop a spatial prisoner’s dilemma model in which Q-learning agents adapt their exploration rates according to local reputation differences, while reputation is updated through an asymmetric, state-dependent rule. The results show that adaptive exploration and asymmetric reputation updating each promote cooperation, but their combination produces a stronger reinforcing effect than either mechanism alone. Low-reputation agents explore more and can recover reputation through cooperation, while high-reputation agents explore less and avoid reputation losses caused by defection. This mechanism also reorganizes cooperation in space, producing a stable checkerboard-like coexistence at intermediate reputation concern. In addition, cooperation is most vulnerable at intermediate baseline exploration rates, whereas stronger asymmetric reputation updating mitigates this exploration-induced disruption. These results suggest that reputation can act not only as a record of past behavior but also as a dynamic signal that regulates exploratory behavior during learning and thereby stabilizes cooperation.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- School of Mathematical Sciences, Beihang University, Beijing 100191, China.
- Key Laboratory of Mathematics, Informatics and Behavioral Semantics, Beihang University, Beijing 100191, China.
- School of Artificial Intelligence, Beihang University, Beijing 100191, China.
- Zhongguancun Laboratory, Beijing 100094, China.
- School of Mathematics and Statistics, Nanjing University of Science and Technology, Nanjing 210094, China.
- Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing, Beihang University, Beijing 100191, China.
ORCID-Profile: An Li, Wenqiang Zhu, Chaoqian Wang, Longzhao Liu, Hongwei Zheng, Yishen Jiang, Xin Wang, Shaoting Tang
Förderung
- National Science and Technology Major Project
- National Natural Science Foundation of China
- Fundamental Research Funds for the Central Universities
- Beijing Natural Science Foundation
- National Cyber Security-National Science and Technology Major Project
- Opening Project of the State Key Laboratory of General Artificial Intelligence
Zitieren
APA
Li, A., Zhu, W., Wang, C., Liu, L., Zheng, H., Jiang, Y., Wang, X., & Tang, S. (2026). Reinforcement learning with reputation-based adaptive exploration promotes cooperation. Chaos: An Interdisciplinary Journal of Nonlinear Science, 36(8). https://doi.org/10.1063/5.0348706
Vancouver
Li A, Zhu W, Wang C, Liu L, Zheng H, Jiang Y, et al. Reinforcement learning with reputation-based adaptive exploration promotes cooperation. Chaos: An Interdisciplinary Journal of Nonlinear Science. 2026;36(8). doi:10.1063/5.0348706
BibTeX
@article{Li2026,
author = {Li, An and Zhu, Wenqiang and Wang, Chaoqian and Liu, Longzhao and Zheng, Hongwei and Jiang, Yishen and Wang, Xin and Tang, Shaoting},
title = {Reinforcement learning with reputation-based adaptive exploration promotes cooperation},
journal = {Chaos: An Interdisciplinary Journal of Nonlinear Science},
year = {2026},
volume = {36},
number = {8},
doi = {10.1063/5.0348706}
}
EUVIMED