arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.08393cs.GT
收藏

NfgTransformer:用于正则形式博弈的等变表示学习

NfgTransformer: Equivariant Representation Learning for Normal-form Games

Siqi Liu, Luke Marris, Georgios Piliouras, Ian Gemp, Nicolas Heess

AI总结:

针对正则形式博弈(NFGs)中策略排列等变性给表示学习带来的挑战,提出NfgTransformer架构,利用该等变性在均衡求解等任务上取得最先进性能,为深度学习系统的博弈论推理铺平道路。

摘要:

正则形式博弈(NFGs)是策略交互的基本模型。我们研究使用神经网络对其进行表示。我们描述了NFGs固有的等变性——策略的任何排列都描述了一个等价的博弈——以及这给表示学习带来的挑战。然后,我们提出了利用这种等变性的NfgTransformer架构,在包括均衡求解、偏离收益估计和排序等一系列博弈论任务中取得了最先进的性能,并提供了一种通用的NFG表示方法。我们表明,由此产生的模型是可解释且通用的,为深度学习系统在与人类及彼此交互时具备博弈论推理能力铺平了道路。

英文摘要:

Normal-form games (NFGs) are the fundamental model of strategic interaction. We study their representation using neural networks. We describe the inherent equivariance of NFGs -- any permutation of strategies describes an equivalent game -- as well as the challenges this poses for representation learning. We then propose the NfgTransformer architecture that leverages this equivariance, leading to state-of-the-art performance in a range of game-theoretic tasks including equilibrium-solving, deviation gain estimation and ranking, with a common approach to NFG representation. We show that the resulting model is interpretable and versatile, paving the way towards deep learning systems capable of game-theoretic reasoning when interacting with humans and with each other.

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。

↑