arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2607.02422cond-mat.dis-nncs.GTphysics.soc-ph
收藏

Sherrington-Kirkpatrick 博弈中的复杂动力学

Complex dynamics in the Sherrington-Kirkpatrick game

King’s College, London(伦敦国王学院)

Desmond Chan, Tobias Galla

AI总结:

研究大量玩家在随机收益矩阵下的自适应学习结果,分析SK博弈的稳定性,发现随机场影响稳定态性质,并引入大正则版本,揭示记忆衰减率和竞争性是决定学习收敛性的关键参数。

摘要:

我们研究了大量玩家参与一系列两人两策略博弈的自适应学习结果。我们关注典型博弈,并在开始时随机生成收益矩阵。收益矩阵在学习过程中保持不变。这为最近由Garnier-Brun、Benzaquen和Bouchaud引入的Sherrington-Kirkpatrick (SK)博弈提供了博弈论基础。这些作者的原模型是一个特例,对任何策略都没有偏向。我们在此确定了具有一般随机偏置的SK博弈的学习稳定性,并发现稳定态的性质受到随机场的影响。我们还引入了SK博弈的大正则版本,其中玩家可以选择弃权。我们确定了该博弈的学习稳定性。我们的分析证实,涉及许多玩家的复杂情况通常是不可学习的,即使每个玩家只选择两种不同的行动。玩家遗忘过去收益的速率和博弈的竞争性成为决定学习是否收敛到唯一不动点、是否存在多个不动点、或者动力学是否持续波动的关键参数。

英文摘要:

We study the outcome of adaptive learning of a large number of players engaging in sets of two-strategy two-player games. We are interested in typical games, and generate the payoff matrices at random at the beginning. The payoff matrices then remain fixed during the learning process. This provides a game theoretic foundation for the Sherrington-Kirkpatrick (SK) game, recently introduced by Garnier-Brun, Benzaquen and Bouchaud. The original model by these authors is a special case, with no bias towards any strategy. We here determine stability of learning for SK games with general random bias, and find that the nature of the stable state is affected by random fields. We also introduce a grand-canonical version of the SK game, in which players can choose to abstain. We determine the stability of learning for this game. Our analysis confirms that complex situations involving many players are frequently unlearnable, even if each player only chooses between two different actions. The rate with which players lose memory of past payoffs and the competitiveness of the game emerge as key parameters determining whether learning converges to a unique fixed point, whether there are many fixed points, or if the dynamics remains persistently volatile.

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。

↑