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 2402.09670cs.GT
收藏

扩展式博弈中低次交换偏差下的高效$Φ$-遗憾最小化

Efficient $Φ$-Regret Minimization with Low-Degree Swap Deviations in Extensive-Form Games

Brian Hu Zhang, Ioannis Anagnostides, Gabriele Farina, Tuomas Sandholm

AI总结:

本文针对扩展式博弈中交换遗憾最小化问题,引入$k$-中介偏差集并开发参数化算法,在特定条件下实现多项式或拟多项式轮数复杂度,填补了现有极端算法间的场景空白。

摘要:

Dagan、Daskalakis、Fishelson和Golowich[2023]以及Peng和Rubinstein[2023]的近期突破性成果建立了一种高效算法,在$N^{\tilde O(1/ε)}$轮内于维度为$N$的扩展式策略空间上实现至多$ε$的交换遗憾。另一方面,Farina和Pipis[2023]开发了一种高效算法,以$\textsf{poly}(N)/ε^2$轮最小化较弱的线性交换遗憾。本文针对这两种极端情况之间的场景开发了高效参数化算法。我们引入$k$-中介偏差集,将Zhang、Farina和Sandholm[2024]近期提出的非定时通信偏差推广至多中介情形,并开发算法以$N^{O(k)}/ε^2$轮最小化针对该偏差集的遗憾。此外,通过将$k$-中介偏差与低次多项式关联,我们证明在分支因子为常数的假设下,针对$k$次多项式交换偏差的遗憾最小化可在$N^{O(kd)^3}/ε^2$轮内实现,其中$d$是博弈深度。对于固定次数$k$,这在贝叶斯博弈中是多项式的,而当$d = \textsf{polylog} N$(博弈树的常见平衡性假设)时更广泛地是拟多项式的。

英文摘要:

Recent breakthrough results by Dagan, Daskalakis, Fishelson and Golowich [2023] and Peng and Rubinstein [2023] established an efficient algorithm attaining at most $ε$ swap regret over extensive-form strategy spaces of dimension $N$ in $N^{\tilde O(1/ε)}$ rounds. On the other extreme, Farina and Pipis [2023] developed an efficient algorithm for minimizing the weaker notion of linear-swap regret in $\mathsf{poly}(N)/ε^2$ rounds. In this paper, we develop efficient parameterized algorithms for regimes between these two extremes. We introduce the set of $k$-mediator deviations, which generalize the untimed communication deviations recently introduced by Zhang, Farina and Sandholm [2024] to the case of having multiple mediators, and we develop algorithms for minimizing the regret with respect to this set of deviations in $N^{O(k)}/ε^2$ rounds. Moreover, by relating $k$-mediator deviations to low-degree polynomials, we show that regret minimization against degree-$k$ polynomial swap deviations is achievable in $N^{O(kd)^3}/ε^2$ rounds, where $d$ is the depth of the game, assuming a constant branching factor. For a fixed degree $k$, this is polynomial for Bayesian games and quasipolynomial more broadly when $d = \mathsf{polylog} N$ -- the usual balancedness assumption on the game tree.

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。

↑