Memory length and space shape multi-agent Q-learning dynamics
Chaos: An Interdisciplinary Journal of Nonlinear Science · 01.04.2026 · 36 (4)
DOI: 10.1063/5.0324979 ↗Kurz gefasst
Fachartikel in der Zeitschrift Chaos: An Interdisciplinary Journal of Nonlinear Science, online erschienen am 13.04.2026. Verfasst von Wei Wang und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Statistics and Mathematics, Yunnan University of Finance and Economics, Kunming 650221, China. Hauptthemen laut MEDLINE: Memory, Learning. Die Arbeit nennt 51 Literaturangaben. Gefördert von: Major project of national philosophy of social science foundation of china, National natural science foundation of china, Key R&D program of yunnan province.
Abstract (Originalsprache)
In repeated interactions, players adjust their behavior based on previous moves. Higher memory leads to an exponential growth in the number of strategies, meaning players require more complex cognitive abilities. Even if players can observe the strategies and payoffs of their co-players, strategies imitated through social learning fail to guarantee effective responses to co-players to bring higher payoffs. We depict the human learning process through reinforcement learning, whereby players learn based on past experiences, independently of the strategies and payoffs of co-players. Here, we explore how different memory lengths and spaces, namely, memory-n, reactive-n, and reactive-n counting, affect the evolution of cooperation among reinforcement learning players. We found that memory-n players maintained higher cooperation than reactive-n players. Notably, higher memory promotes cooperation in memory-n players but inhibits it in reactive-n players. Reactive-n counting players can alleviate the negative effects of excessive memory by compressing the memory. Strategies with the nature of mutual cooperation and retaliation are key for reinforcement learning players to maintain cooperation. Our research highlights that judiciously adjusting the information available to players more effectively fosters cooperation within multi-agent systems.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- School of Statistics and Mathematics, Yunnan University of Finance and Economics, Kunming 650221, China.
- Research Institute of Data Science, Shanghai Lixin University of Accounting and Finance, Shanghai 201209, China.
ORCID-Profile: Wei Wang, Xiaogang Li, Yongjuan Ma, Huaiyu Tan, Lei Shi
Förderung
- Major project of national philosophy of social science foundation of china
- National natural science foundation of china
- Key R&D program of yunnan province
- NSF of yunnan province
- Yunnan University of Finance and Economics fund project
Zitieren
APA
Wang, W., Li, X., Ma, Y., Tan, H., & Shi, L. (2026). Memory length and space shape multi-agent Q-learning dynamics. Chaos: An Interdisciplinary Journal of Nonlinear Science, 36(4). https://doi.org/10.1063/5.0324979
Vancouver
Wang W, Li X, Ma Y, Tan H, Shi L. Memory length and space shape multi-agent Q-learning dynamics. Chaos: An Interdisciplinary Journal of Nonlinear Science. 2026;36(4). doi:10.1063/5.0324979
BibTeX
@article{Wang2026,
author = {Wang, Wei and Li, Xiaogang and Ma, Yongjuan and Tan, Huaiyu and Shi, Lei},
title = {Memory length and space shape multi-agent Q-learning dynamics},
journal = {Chaos: An Interdisciplinary Journal of Nonlinear Science},
year = {2026},
volume = {36},
number = {4},
doi = {10.1063/5.0324979}
}
EUVIMED