Reputation-Based Interaction Promotes Cooperation With Reinforcement Learning

强化学习 计算机科学 声誉 人工智能 钢筋 工程类 社会科学 结构工程 社会学
作者
Tianyu Ren,Xiao‐Jun Zeng
出处
期刊:IEEE Transactions on Evolutionary Computation [Institute of Electrical and Electronics Engineers]
卷期号:28 (4): 1177-1188 被引量:33
标识
DOI:10.1109/tevc.2023.3304911
摘要

Dynamical interaction represents a fundamental coevolutionary rule that addresses the intricacies of cooperation in social dilemmas. It provides a normative account for the changes in ties within interaction networks in response to the behaviour of social partners. While considerable efforts have explored the role of partner selection in fostering cooperation, there remains a limited understanding of how agents learn to establish effective interaction patterns and adapt their connections accordingly. To bridge this knowledge gap, we leverage recent advancements in reinforcement learning and propose an adaptive interaction mechanism to investigate self-organization behaviour in the iterated prisoner’s dilemma game. Within this framework, artificial agents are trained using a self-regarding Roth-Erev algorithm, utilizing reputation as a dynamic signal to update their willingness to engage with neighbours. Additionally, these agents are endowed with the capability to sever inactive connections. Simulation results demonstrate the effectiveness of utilizing reinforcement learning and local information from reputation to capture the dynamics of interactions. Notably, we discover that the entangled coevolution of strategy and interaction network can facilitate the emergence and maintenance of cooperation, despite the optimal tolerance threshold for ineffective neighbours varying depending on the strength of the social dilemma. Furthermore, the emerging network topology presented in this work accurately captures the assortative mixing pattern observed in previous experiments and realistic evidence. Finally, we validate the simulation results through theoretical analysis and confirm the robustness of the proposed mechanism across populations of varying sizes and initial structures.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
在水一方的应助被AishuangQi采纳,获得10
刚刚
yyy完成签到,获得积分20
刚刚
工作热情仔的应助被mutsumi采纳,获得350
刚刚
yuanyingge完成签到,获得积分10
刚刚
1秒前
细腻的念之完成签到,获得积分20
1秒前
1秒前
1秒前
1秒前
Atheist完成签到,获得积分10
1秒前
yoowt发布了新的文献求助10
1秒前
1秒前
1秒前
2秒前
宝z发布了新的文献求助10
2秒前
斯文败类的应助被淡定采纳,获得10
2秒前
wxm的应助被California采纳,获得10
2秒前
ohh完成签到,获得积分10
2秒前
STaoY完成签到,获得积分10
2秒前
2秒前
2秒前
Rtian发布了新的文献求助10
3秒前
May发布了新的文献求助10
3秒前
搜集达人的应助被Ava采纳,获得10
3秒前
3秒前
科研通AI6.4的应助被CClaire采纳,获得10
3秒前
乐事小黄瓜完成签到,获得积分10
3秒前
李健的应助被米饭采纳,获得10
3秒前
程绪洋完成签到 ,获得积分10
4秒前
就爱吃抹茶完成签到 ,获得积分10
4秒前
nemo711完成签到,获得积分10
4秒前
SciGPT的应助被SGLY采纳,获得10
4秒前
ZJB完成签到,获得积分10
4秒前
4秒前
鸟鸣完成签到,获得积分10
5秒前
5秒前
5秒前
5秒前
5秒前
5秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1500
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
John McDowells Bildungstheorie 800
八旗制度の研究 600
Analyses de reconnaissances de dettes passées devant les échevins d'Ypres (1249-1291) 600
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8159929
求助须知:如何正确求助?哪些是违规求助? 9555266
关于积分的说明 21726335
捐赠科研通 7749807
什么是DOI,文献DOI怎么找? 3427310
关于科研通互助平台的介绍 2552391
邀请新用户注册赠送积分活动 2471654