Using privileged information during training can improve the sample
efficiency and performance of machine learning systems. This paradigm has been
applied to reinforcement learning (RL), primarily in the form of distillation
or auxiliary tasks, and less commonly in the form of augmenting the inputs of
agents. In this work, we investigate Privileged Information Dropout (\pid) for
achieving the latter which can be applied equally to value-based and
policy-based RL algorithms. Within a simple partially-observed environment, we
demonstrate that \pid outperforms alternatives for leveraging privileged
information, including distillation and auxiliary tasks, and can successfully
utilise different types of privileged information. Finally, we analyse its
effect on the learned representations.

本研究探讨了运用特权信息（privileged information）提高机器学习系统的样本效率和性能的方法，研究表明采用 Privileged Information Dropout 在强化学习任务中（无论是基于值还是基于策略的 RL 算法）都比其他方法如蒸馏（distillation）和辅助任务（auxiliary task）具有更优的性能，并能够成功利用不同类型的特权信息，最后分析了其对学习表现的影响。