We provide a unifying view of a large family of previous imitation learning algorithms through the lens of moment matching. At its core, our classification scheme is based on whether the learner attempts to match (1) reward or (2) action-value moments of the expert's behavior, with each option leading to differing algorithmic approaches. By considering adversarially chosen divergences between learner and expert behavior, we are able to derive bounds on policy performance that apply for all algorithms in each of these classes, the first to our knowledge. We also introduce the notion of recoverability, implicit in many previous analyses of imitation learning, which allows us to cleanly delineate how well each algorithmic family is able to mitigate compounding errors. We derive two novel algorithm templates, AdVIL and AdRIL, with strong guarantees, simple implementation, and competitive empirical performance.

我们通过矩匹配的视角提供了先前大量的模仿学习算法的统一观点，并考虑了学习者和专家之间行为差异之间的分歧以派生出适用于每个算法类别中的所有算法的策略性能的界限。 我们引入了矩恢复的概念，使我们能够清晰地划分每个算法家族的表现如何缓解复合误差，并推导出三种具有强有力的保证，简单实现和有竞争力的经验性能的算法模板（AdVIL，AdRIL和DAeQuIL）。

时刻与匹配：一个用于弥合模仿差距的博弈理论框架