arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1105.0523physics.soc-phcond-mat.stat-mech
收藏

竞争性学习的动力学:更新和记忆的作用

The dynamics of competitive learning: the role of updates and memory

Ajaz Ahmad Bhat, Anita Mehta

摘要:

我们研究的记忆和不同的更新范式的竞争性学习的博弈论模型中,代理商的影响,在他们的战略选择的选择,以及随之而来的成功率,他们的近邻。我们在所有可能的组合中应用并行和顺序更新的两个竞争规则,并发现,通常情况下,该模型的相图由一个无序相分离的两个有序相共存。一个主要结果是相应的临界指数属于选民模型的广义普适类。当这两种策略是不同的,但不是太不同,我们发现预期的线性响应行为作为其difference.Finally的函数,我们看看极端的情况下,一个优越的策略,伴随着较早的结果的短记忆,是对它的逆,有趣的是,我们发现,较早的结果的长记忆偶尔可以补偿全局劣势策略的选择。

英文摘要:

We examine the effects of memory and different updating paradigms in a game-theoretic model of competitive learning, where agents are influenced in their choice of strategy by both the choices made by, and the consequent success rates of, their immediate neighbours. We apply parallel and sequential updates in all possible combinations to the two competing rules, and find, typically, that the phase diagram of the model consists of a disordered phase separating two ordered phases at coexistence. A major result is that the corresponding critical exponents belong to the generalised universality class of the voter model. When the two strategies are distinct but not too different, we find the expected linear response behaviour as a function of their difference.Finally, we look at the extreme situation when a superior strategy, accompanied by a short memory of earlier outcomes, is pitted against its inverse; interestingly, we find that a long memory of earlier outcomes can occasionally compensate for the choice of a globally inferior strategy.

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。

↑