[论文解读] The route to chaos in routing games: When is Price of Anarchy too optimistic?

Thiparat Chotibut, Fryderyk Falniowski+2 more|arXiv (Cornell University)|Jun 6, 2019

Game Theory and Applications参考文献 80被引用 5

一句话总结

本文表明，在具有线性成本的简单非原子路由博弈中——即使社会最优性价格（PoA）恰好为1——随着系统需求增加，乘法权重更新（MWU）动态仍可能变得不稳定且混沌。尽管均衡状态为社会最优，但由于倍周期分岔和Li-Yorke混沌，时间平均社会成本可能达到最差可能值，从而削弱了如PoA等均衡度量的预测能力。

ABSTRACT

Routing games are amongst the most studied classes of games. Their two most well-known properties are that learning dynamics converge to equilibria and that all equilibria are approximately optimal. In this work, we perform a stress test for these classic results by studying the ubiquitous dynamics, Multiplicative Weights Update, in different classes of congestion games, uncovering intricate non-equilibrium phenomena. As the system demand increases, the learning dynamics go through period-doubling bifurcations, leading to instabilities, chaos and large inefficiencies even in the simplest case of non-atomic routing games with two paths of linear cost where the Price of Anarchy is equal to one. Starting with this simple class, we show that every system has a carrying capacity, above which it becomes unstable. If the equilibrium flow is a symmetric $50-50\%$ split, the system exhibits one period-doubling bifurcation. A single periodic attractor of period two replaces the attracting fixed point. Although the Price of Anarchy is equal to one, in the large population limit the time-average social cost for all but a zero measure set of initial conditions converges to its worst possible value. For asymmetric equilibrium flows, increasing the demand eventually forces the system into Li-Yorke chaos with positive topological entropy and periodic orbits of all possible periods. Remarkably, in all non-equilibrating regimes, the time-average flows on the paths converge exactly to the equilibrium flows, a property akin to no-regret learning in zero-sum games. These results are robust. We extend them to routing games with arbitrarily many strategies, polynomial cost functions, non-atomic as well as atomic routing games and heteregenous users. Our results are also applicable to any sequence of shrinking learning rates, e.g., $1/\sqrt{T}$, by allowing for a dynamically increasing population size.

研究动机与目标

• 研究在拥挤博弈的学习动态中，基于均衡的效率保证（如社会最优性价格）的鲁棒性。
• 检验在系统需求增加时，学习动态是否仍能收敛至纳什均衡。
• 识别在简单路由博弈中，MWU导致非均衡、混沌行为的条件。
• 探索在非均衡状态下，时间平均性能、遗憾与社会成本之间的关系。
• 将研究结果扩展至原子、非原子、多项式成本及异构用户拥挤博弈。

提出的方法

• 分析双策略非原子拥挤博弈中乘法权重更新（MWU）的动力学行为，其成本函数为线性函数。
• 利用分岔理论与动力系统分析，识别系统从稳定均衡到极限环及混沌的转变过程。
• 推导出临界参数 $ a = (α + β)N \ln(1/(1-\epsilon)) $，该参数决定系统是否在步长减小的情况下仍保持混沌状态。
• 通过倍周期分岔的Feigenbaum混沌路径，刻画不稳定性出现的机制。
• 通过分析与数值验证，将结果推广至多策略博弈、多项式成本函数、原子博弈及异构用户场景。
• 证明即使在混沌状态下，时间平均流量仍收敛至均衡值，这一性质类似于零和博弈中的无遗憾学习。

实验结果

研究问题

• RQ1 在何种条件下，乘法权重更新算法在非原子路由博弈中无法收敛至均衡？
• RQ2 随着系统需求增加，社会最优性价格为1的拥挤博弈中，学习动态的稳定性如何变化？
• RQ3 即使所有均衡均为社会最优，简单拥挤博弈中是否仍可能产生混沌动态？
• RQ4 时间平均社会成本与系统动力学状态（均衡 vs. 混沌）之间存在何种关系？
• RQ5 在非均衡、混沌状态下，时间平均流量与成本在多大程度上仍接近均衡值？

主要发现

• 对于对称均衡流量（50-50分配），增加需求会触发一次倍周期分岔，导致周期为二的稳定极限环。
• 在大群体极限下，几乎所有初始条件下，时间平均社会成本均收敛至最差可能值，尽管PoA = 1。
• 对于非对称均衡流量，增加需求将导致Li-Yorke混沌，具有正的拓扑熵及所有可能周期的周期轨道。
• 即使在混沌状态下，各路径上的时间平均流量仍精确收敛至纳什均衡流量，这一性质类似于无遗憾学习。
• 系统具有有限承载能力：超过此阈值后，无论学习率如何减小，动态均变为非均衡且低效。
• 若群体规模缓慢增加（例如随时间亚线性增长），即使步长如 $1/\sqrt{n}$ 逐渐减小，系统仍可长期维持在混沌状态。