ABSTRACT

In divergent interest tacit coordination games there is a tradeoff between selecting a solution with a high individual payoff and one which is perceptually more salient to both players, i.e., a focal point. To construct a cognitive model of decision making in such games we need to consider both the social value orientation of the players and the game features. Therefore, the goal of this study was to construct a cognitive model for predicting the probability of selecting a focal point solution in these types of games. Using bootstrap aggregated ensemble of decision trees that was trained on the “bargaining table’ game behavioural data were able to predict when players will select a focal point solution. The binary classification achieved an accuracy level of 85%. The main contribution of the current study is the ability to model players behaviour based on the interaction between different SVOs and game features. This interaction enabled us to gain different insights regarding player’s behaviour. For example, a prosocial player often showed a tendency towards focal point solutions even when their personal gains were lower than that of the co-player. Thus, SVO is not a sufficient model for explaining behaviour in different divergent interest scenarios.

摘要

在利益发散的默契协调博弈中，需要在选择具有高个人收益的解决方案和选择对双方参与者感知更显着的解决方案（即焦点）之间进行权衡。构建此类游戏决策的认知模型需要考虑玩家的社会价值取向和游戏特征。因此，本研究的目标是构建一个认知模型来预测在此类游戏中选择焦点解决方案的概率。使用在“讨价还价桌”游戏行为数据上训练的决策树的引导聚合集合能够预测玩家何时选择焦点解决方案。二元分类的准确率达到 85%。当前研究的主要贡献是能够根据不同 SVO 和游戏特征之间的交互来建模玩家行为。这种互动使我们能够获得有关玩家行为的不同见解。例如，亲社会玩家经常表现出寻求焦点解决方案的倾向，即使他们的个人收益低于共同玩家。因此，SVO 不足以解释不同不同兴趣场景中的行为。