To optimally coordinate with others in cooperative games, it is often crucial to have information about one's collaborators: successful driving requires understanding which side of the road to drive on. However, not every feature of collaborators is strategically relevant: the fine-grained acceleration of drivers may be ignored while maintaining optimal coordination. We show that there is a well-defined dichotomy between strategically relevant and irrelevant information. Moreover, we show that, in dynamic games, this dichotomy has a compact representation that can be efficiently computed via a Bellman backup operator. We apply this algorithm to analyze the strategically relevant information for tasks in both a standard and a partially observable version of the Overcooked environment. Theoretical and empirical results show that our algorithms are significantly more efficient than baselines. Videos are available at https://minknowledge.github.io.

翻译：在合作博弈中，为了与他人实现最优协调，通常需要掌握关于协作者的信息：成功驾驶需要理解应该在道路的哪一侧行驶。然而，并非协作者的每一个特征都具有战略相关性：驾驶员细微的加速度变化可能被忽略，同时仍能保持最优协调。我们证明，战略相关与不相关信息之间存在明确的分界线。此外，我们表明，在动态博弈中，这种分界线可以通过贝尔曼备份算子高效计算，从而获得紧凑表示。我们将该算法应用于分析标准版和部分可观测版的“Overcooked”环境中的战略相关信息。理论和实验结果表明，我们的算法显著优于基线方法。视频见 https://minknowledge.github.io。