论文标题
使用合作游戏抽象评估和奖励团队合作
Evaluating and Rewarding Teamwork Using Cooperative Game Abstractions
论文作者
论文摘要
我们可以预测一个个人团队的表现如何？个人应该为团队绩效做出贡献而获得奖励？合作游戏理论为我们提供了一组强大的工具来回答这些问题：特征功能（CF）和解决方案概念（例如Shapley Value（SV））。将这些技术应用于现实世界问题有两个主要困难：首先，CF很少给我们，需要从数据中学习。其次，SV本质上是合并的。我们介绍了一个称为合作游戏抽象（CGA）的参数模型，用于从数据估算CFS。 CGA易于学习，易于解释，并且至关重要的是允许对SV的线性时间计算。我们为CGA模型提供了识别结果和样品复杂性界限，以及使用CGA的SV估计中的误差界限。我们将方法应用于研究人造RL代理团队以及专业运动的现实世界团队。
Can we predict how well a team of individuals will perform together? How should individuals be rewarded for their contributions to the team performance? Cooperative game theory gives us a powerful set of tools for answering these questions: the Characteristic Function (CF) and solution concepts like the Shapley Value (SV). There are two major difficulties in applying these techniques to real world problems: first, the CF is rarely given to us and needs to be learned from data. Second, the SV is combinatorial in nature. We introduce a parametric model called cooperative game abstractions (CGAs) for estimating CFs from data. CGAs are easy to learn, readily interpretable, and crucially allow linear-time computation of the SV. We provide identification results and sample complexity bounds for CGA models as well as error bounds in the estimation of the SV using CGAs. We apply our methods to study teams of artificial RL agents as well as real world teams from professional sports.
