arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2412.20116cs.GTphysics.soc-ph
收藏

网络上全有或全无公共品博弈中的多智能体强化学习

Multi-agent reinforcement learning in the all-or-nothing public goods game on networks

Benedikt Valentin Meylahn

AI总结:

本文研究网络上全有或全无公共品博弈中的多智能体强化学习,证明其长期收敛于全贡献或全背叛,并发现复杂网络中的亚稳态及网络密度与贡献率的负相关关系。

摘要:

我们通过网络上智能体之间的全有或全无公共品博弈来研究人际信任。智能体被赋予简单但具有适应性的学习规则,即指数移动平均,借此估计其网络中邻居的行为。理论上我们证明,在长时间极限下,这一多智能体强化学习过程最终总是导致对公共品的无限贡献或无限背叛(没有智能体为公共品做出贡献)。然而,通过对极限前行为的模拟,我们看到在复杂网络结构上可能存在混合状态,在这些状态中,过程似乎在真正收敛到智能体信念和行为完全相同的状态之前趋于稳定。在这些亚稳态中,局部网络特征可以决定智能体对其邻居的信任是高还是低。更一般地,我们发现网络越密集,对公共品的贡献率越低。这对于如何通过促成更小的局部互动来传播面向公共品的全局贡献具有启示意义。

英文摘要:

We study interpersonal trust by means of the all-or-nothing public goods game between agents on a network. The agents are endowed with the simple yet adaptive learning rule, exponential moving average, by which they estimate the behavior of their neighbors in the network. Theoretically we show that in the long-time limit this multi-agent reinforcement learning process always eventually results in indefinite contribution to the public good or indefinite defection (no agent contributing to the public good). However, by simulation of the pre-limit behavior, we see that on complex network structures there may be mixed states in which the process seems to stabilize before actual convergence to states in which agent beliefs and actions are all the same. In these metastable states the local network characteristics can determine whether agents have high or low trust in their neighbors. More generally it is found that more dense networks result in lower rates of contribution to the public good. This has implications for how one can spread global contribution toward a public good by enabling smaller local interactions.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑