Evolutionary multi-agent reinforcement learning in group social dilemmas
Chaos: An Interdisciplinary Journal of Nonlinear Science · 01.02.2025 · 35 (2)
DOI: 10.1063/5.0246332 ↗Kurz gefasst
Fachartikel in der Zeitschrift Chaos: An Interdisciplinary Journal of Nonlinear Science, online erschienen am 12.02.2025. Verfasst von B Mintz und 1 weiteren Autor:innen. Beteiligte Einrichtung: Mathematics Department, Dartmouth College, Hanover, New Hampshire 03755, USA. Hauptthemen laut MEDLINE: Game Theory, Machine Learning, Reinforcement, Psychology, Biological Evolution. Die Arbeit wurde bisher 22-mal zitiert (Crossref) und nennt 75 Literaturangaben. Gefördert von: Dartmouth College.
Abstract (Originalsprache)
Reinforcement learning (RL) is a powerful machine learning technique that has been successfully applied to a wide variety of problems. However, it can be unpredictable and produce suboptimal results in complicated learning environments. This is especially true when multiple agents learn simultaneously, which creates a complex system that is often analytically intractable. Our work considers the fundamental framework of Q-learning in public goods games, where RL individuals must work together to achieve a common goal. This setting allows us to study the tragedy of the commons and free-rider effects in artificial intelligence cooperation, an emerging field with potential to resolve challenging obstacles to the wider application of artificial intelligence. While this social dilemma has been mainly investigated through traditional and evolutionary game theory, our work connects these two approaches by studying agents with an intermediate level of intelligence. We consider the influence of learning parameters on cooperation levels in simulations and a limiting system of differential equations, as well as the effect of evolutionary pressures on exploration rate in both of these models. We find selection for higher and lower levels of exploration, as well as attracting values, and a condition that separates these in a restricted class of games. Our work enhances the theoretical understanding of recent techniques that combine evolutionary algorithms with Q-learning and extends our knowledge of the evolution of machine behavior in social dilemmas.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Mathematics Department, Dartmouth College, Hanover, New Hampshire 03755, USA.
Förderung
- Dartmouth College
Zitieren
APA
Mintz, B., & Fu, F. (2025). Evolutionary multi-agent reinforcement learning in group social dilemmas. Chaos: An Interdisciplinary Journal of Nonlinear Science, 35(2). https://doi.org/10.1063/5.0246332
Vancouver
Mintz B, Fu F. Evolutionary multi-agent reinforcement learning in group social dilemmas. Chaos: An Interdisciplinary Journal of Nonlinear Science. 2025;35(2). doi:10.1063/5.0246332
BibTeX
@article{Mintz2025,
author = {Mintz, B and Fu, F},
title = {Evolutionary multi-agent reinforcement learning in group social dilemmas},
journal = {Chaos: An Interdisciplinary Journal of Nonlinear Science},
year = {2025},
volume = {35},
number = {2},
doi = {10.1063/5.0246332}
}
EUVIMED