arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1606.06244cs.GTcs.LG
收藏

游戏中的学习:快速收敛的鲁棒性

Learning in Games: Robustness of Fast Convergence

Cornell University(康奈尔大学);Tsinghua University(清华大学)

Dylan J. Foster, Zhiyuan Li, Thodoris Lykouris, Karthik Sridharan, Eva Tardos

摘要:

我们表明,学习算法满足$\textit{low approximate regret}$属性的经验快速收敛到近似最优的一大类重复的游戏。我们的性质,简单地要求每个学习者有小的遗憾相比,$(1+ε)$ -乘法近似的最佳行动在事后看来,是无处不在的学习算法,它是满足甚至香草对冲预测。我们的研究结果在许多方面改进了Syrgkanis等人[SALS 15]的近期工作。我们只要求参与者观察其他参与者的已实现行为下的收益,而不是预期收益。我们进一步表明,收敛发生的概率很高,并显示收敛下的强盗反馈。最后,我们提高了收敛速度的一个因素$n$,球员的数量。我们的分析提供了快速收敛的设置和算法类的范围比以前的工作要广泛得多。我们的框架适用于动态人口游戏,通过低近似的遗憾属性的变化专家。在这里,我们以两种方式加强了Lykouris等人的结果。[LST 16]:我们允许玩家从更大的类中选择学习算法,其中包括基本对冲算法的一个小变体,并且我们增加了达到近似最优的玩家的最大流失。在强盗设置,我们提出了一个新的算法,它提供了一个“小损失”型的界限,改善依赖于效用设置中的行动的数量,是既简单又有效。这一结果可能是独立的利益。

英文摘要:

We show that learning algorithms satisfying a $\textit{low approximate regret}$ property experience fast convergence to approximate optimality in a large class of repeated games. Our property, which simply requires that each learner has small regret compared to a $(1+ε)$-multiplicative approximation to the best action in hindsight, is ubiquitous among learning algorithms; it is satisfied even by the vanilla Hedge forecaster. Our results improve upon recent work of Syrgkanis et al. [SALS15] in a number of ways. We require only that players observe payoffs under other players' realized actions, as opposed to expected payoffs. We further show that convergence occurs with high probability, and show convergence under bandit feedback. Finally, we improve upon the speed of convergence by a factor of $n$, the number of players. Both the scope of settings and the class of algorithms for which our analysis provides fast convergence are considerably broader than in previous work. Our framework applies to dynamic population games via a low approximate regret property for shifting experts. Here we strengthen the results of Lykouris et al. [LST16] in two ways: We allow players to select learning algorithms from a larger class, which includes a minor variant of the basic Hedge algorithm, and we increase the maximum churn in players for which approximate optimality is achieved. In the bandit setting we present a new algorithm which provides a "small loss"-type bound with improved dependence on the number of actions in utility settings, and is both simple and efficient. This result may be of independent interest.

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。

↑