arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2409.02706cs.GT
收藏

超越纳什均衡:利用信念更新虚拟博弈实现贝叶斯完美均衡

Beyond Nash Equilibrium: Achieving Bayesian Perfect Equilibrium with Belief Update Fictitious Play

Qi Ju, Zhemei Fang, Yunfeng Luo

AI总结:

本文提出信念更新虚拟博弈(BUFP),通过融合虚拟博弈与信念更新并调节迭代步长,在不完全信息扩展式博弈中同时实现纳什均衡和贝叶斯完美均衡,实验表明其在被支配策略场景下收益较传统CFR提升48.53%。

摘要:

在机器学习与博弈论领域,在不完全信息扩展式博弈中寻求纳什均衡(NE)既具挑战性又至关重要,有助于提升人工智能在多样场景下的决策支持能力。传统的反事实遗憾最小化(CFR)技术在逼近纳什均衡方面表现出色,主要关注对手采用最优策略的情形。然而,机器学习在策略博弈中的本质不仅限于对最优行动作出反应,还包括在所有情境下辅助人类决策。这不仅涉及针对最优策略制定应对方案,还涵盖从次优决策中恢复以及利用对手的失误。正因如此,从纳什均衡过渡到贝叶斯完美均衡(BPE)具有重要意义,因为BPE考虑了每一种可能的情况,包括对手的非理性行为。为弥合这一差距,我们提出了信念更新虚拟博弈(BUFP),该方法创新性地将虚拟博弈与信念相结合,以BPE为目标,而BPE是比纳什均衡更全面的均衡概念。具体而言,通过调整迭代步长,BUFP能够策略性地收敛到纳什均衡和贝叶斯完美均衡。例如,在我们的实验中,BUFP(EF)利用扩展式虚拟博弈(EFFP)的步长来实现贝叶斯完美均衡,在存在被支配策略的场景中,其收益比传统CFR提高了48.53%。

英文摘要:

In the domain of machine learning and game theory, the quest for Nash Equilibrium (NE) in extensive-form games with incomplete information is challenging yet crucial for enhancing AI's decision-making support under varied scenarios. Traditional Counterfactual Regret Minimization (CFR) techniques excel in navigating towards NE, focusing on scenarios where opponents deploy optimal strategies. However, the essence of machine learning in strategic game play extends beyond reacting to optimal moves; it encompasses aiding human decision-making in all circumstances. This includes not only crafting responses to optimal strategies but also recovering from suboptimal decisions and capitalizing on opponents' errors. Herein lies the significance of transitioning from NE to Bayesian Perfect Equilibrium (BPE), which accounts for every possible condition, including the irrationality of opponents. To bridge this gap, we propose Belief Update Fictitious Play (BUFP), which innovatively blends fictitious play with belief to target BPE, a more comprehensive equilibrium concept than NE. Specifically, through adjusting iteration stepsizes, BUFP allows for strategic convergence to both NE and BPE. For instance, in our experiments, BUFP(EF) leverages the stepsize of Extensive Form Fictitious Play (EFFP) to achieve BPE, outperforming traditional CFR by securing a 48.53\% increase in benefits in scenarios characterized by dominated strategies.

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。

↑