arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2102.05264cs.AIcs.LG
收藏

通过多武装强盗进行玩家建模

Player Modeling via Multi-Armed Bandits

Drexel University(德雷塞尔大学);Rowan University(罗文大学)

Robert C. Gray, Jichen Zhu, Dannielle Arigo, Evan Forman, Santiago Ontañón

摘要:

本文主要研究在自适应游戏中,仅从玩家行为出发构建个性化玩家模型。我们提出了两个主要的贡献:第一个是一种新的方法,球员建模的基础上多武装土匪(MABs)。该方法同时并且以原则性的方式解决了收集数据以对当前玩家感兴趣的特征进行建模的问题以及基于该模型来适配交互式体验的问题。其次,我们提出了一种方法来评估和微调这些算法之前,在用户研究中生成数据。这是一个重要的问题,因为进行用户研究是一个昂贵且劳动密集型的过程;因此,事先评估算法的能力可以节省大量资源。我们评估我们的方法在建模玩家的社会比较取向(SCO)的背景下,目前的实证结果,从模拟和真实的球员。

英文摘要:

This paper focuses on building personalized player models solely from player behavior in the context of adaptive games. We present two main contributions: The first is a novel approach to player modeling based on multi-armed bandits (MABs). This approach addresses, at the same time and in a principled way, both the problem of collecting data to model the characteristics of interest for the current player and the problem of adapting the interactive experience based on this model. Second, we present an approach to evaluating and fine-tuning these algorithms prior to generating data in a user study. This is an important problem, because conducting user studies is an expensive and labor-intensive process; therefore, an ability to evaluate the algorithms beforehand can save a significant amount of resources. We evaluate our approach in the context of modeling players' social comparison orientation (SCO) and present empirical results from both simulations and real players.

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。

↑