Oscillatory evolution of collective behavior in evolutionary games played with reinforcement learning
| Autor: | Li Chen, Xu-Dong Liu, Si-Ping Zhang, Ji-Qiang Zhang |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Physics - Physics and Society
Collective behavior Computer science media_common.quotation_subject FOS: Physical sciences Aerospace Engineering Ocean Engineering Physics and Society (physics.soc-ph) 01 natural sciences 0103 physical sciences Evolutionary game dynamics Reinforcement learning Electrical and Electronic Engineering 010301 acoustics media_common Structure (mathematical logic) Cognitive science Applied Mathematics Mechanical Engineering Stochastic game Perspective (graphical) Nonlinear Sciences - Adaptation and Self-Organizing Systems Action (philosophy) Control and Systems Engineering Imitation Adaptation and Self-Organizing Systems (nlin.AO) |
| Zdroj: | Nonlinear Dynamics. 99:3301-3312 |
| ISSN: | 1573-269X 0924-090X |
| DOI: | 10.1007/s11071-019-05398-4 |
| Popis: | Large-scale cooperation underpins the evolution of ecosystems and the human society, and the collective behaviors by self-organization of multi-agent systems are the key for understanding. As artificial intelligence (AI) prevails in almost all branches of science, it would be of great interest to see what new insights of collective behavior could be obtained from a multi-agent AI system. Here, we introduce a typical reinforcement learning (RL) algorithm -- Q learning into evolutionary game dynamics, where agents pursue optimal action on the basis of the introspectiveness rather than the birth-death or imitation processes in the traditional evolutionary game (EG). We investigate the cooperation prevalence numerically for a general $2\times 2$ game setting. We find that the cooperation prevalence in the multi-agent AI is amazing of an equal level as in the traditional EG in most cases. However, in the snowdrift games with RL we also reveal that explosive cooperation appears in the form of periodic oscillation, and we study the impact of the payoff structure on its emergence. Finally, we show that the periodic oscillation can also be observed in some other EGs with the RL algorithm, such as the rock-paper-scissors game. Our results offer a reference point to understand emergence of cooperation and oscillatory behaviors in nature and society from AI's perspective. Comment: 10 pages, 7 figures |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full text from SpringerLink