arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2302.06969math.DSmath.PR
收藏

零和博弈中复制者动力学的随机变体及其不变测度

A stochastic variant of replicator dynamics in zero-sum games and its invariant measures

Maximilian Engel, Georgios Piliouras

AI总结:

研究零和博弈中复制者动力学随机变体的行为,通过不变测度证明其质量集中于纯策略轮廓,揭示了随机扰动下 Nash 均衡预测与演化涌现行为的显著分歧。

摘要:

我们研究了两智能体零和博弈中复制者动力学随机变体的行为。我们通过不变测度刻画了此类系统的统计特性,并证明这些不变测度完全支撑于混合策略空间的边界上。根据噪声强度,我们还能通过发现质量在边界特定部分的积累来进一步刻画这些不变测度。特别地,无论噪声大小如何,我们证明了任何不变概率测度都是纯策略轮廓上 Dirac 测度的凸组合,这些纯策略轮廓对应于智能体单纯形的顶点/角。因此,在存在随机扰动的情况下,即使在如 Matching Pennies 这样最经典的零和博弈中,我们也能观察到 Nash 均衡的公理化预测与基于随机自适应学习智能体假设推导出的演化涌现行为之间存在显著分歧。

英文摘要:

We study the behavior of a stochastic variant of replicator dynamics in two-agent zero-sum games. We characterize the statistics of such systems by their invariant measures which can be shown to be entirely supported on the boundary of the space of mixed strategies. Depending on the noise strength we can furthermore characterize these invariant measures by finding accumulation of mass at specific parts of the boundary. In particular, regardless of the magnitude of noise, we show that any invariant probability measure is a convex combination of Dirac measures on pure strategy profiles, which correspond to vertices/corners of the agents' simplices. Thus, in the presence of stochastic perturbations, even in the most classic zero-sum settings, such as Matching Pennies, we observe a stark disagreement between the axiomatic prediction of Nash equilibrium and the evolutionary emergent behavior derived by an assumption of stochastically adaptive, learning agents.

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。

↑