arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1102.0876physics.soc-phcs.GTq-bio.PE
收藏

随机博弈学习中的固定时间和逃逸时间

Fixation and escape times in stochastic game learning

John Realpe-Gomez, Bartosz Szczesny, Luca Dall'Asta, Tobias Galla

摘要:

已知有限种群中的进化动力学在没有突变的情况下最终会固定。我们在这里发现,一个类似的现象,可以发现在随机游戏动态批量学习,并调查固定在一个简单的2x2游戏的学习过程中,两个玩家的游戏与循环互动,并在最佳网络游戏的背景下。进化中有限种群的类似物在这里是策略更新之间的有限批观察。我们研究了何时以及如何固定可以发生,并提出了从数值模拟的平均时间固定的结果。简单的情况下,也服从分析方法,我们提供了所谓的逃逸时间作为批量大小的函数的行为的估计。讨论了在进化动力学中与逃避和固定的异同。

英文摘要:

Evolutionary dynamics in finite populations is known to fixate eventually in the absence of mutation. We here show that a similar phenomenon can be found in stochastic game dynamical batch learning, and investigate fixation in learning processes in a simple 2x2 game, for two-player games with cyclic interaction, and in the context of the best-shot network game. The analogues of finite populations in evolution are here finite batches of observations between strategy updates. We study when and how such fixation can occur, and present results on the average time-to-fixation from numerical simulations. Simple cases are also amenable to analytical approaches and we provide estimates of the behaviour of so-called escape times as a function of the batch size. The differences and similarities with escape and fixation in evolutionary dynamics are discussed.

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。

↑