Informational parsimony -- i.e., using the minimal information required for a task, -- provides a useful inductive bias for learning representations that achieve better generalization by being robust to noise and spurious correlations. We propose information gating in the pixel space as a way to learn more parsimonious representations. Information gating works by learning masks that capture only the minimal information required to solve a given task. Intuitively, our models learn to identify which visual cues actually matter for a given task. We gate information using a differentiable parameterization of the signal-to-noise ratio, which can be applied to arbitrary values in a network, e.g.~masking out pixels at the input layer. We apply our approach, which we call InfoGating, to various objectives such as: multi-step forward and inverse dynamics, Q-learning, behavior cloning, and standard self-supervised tasks. Our experiments show that learning to identify and use minimal information can improve generalization in downstream tasks -- e.g., policies based on info-gated images are considerably more robust to distracting/irrelevant visual features.
翻译:信息光谱 -- -- 即使用一项任务所需的最起码信息,为学习显示提供了一种有用的感化偏差,通过对噪音和虚假的相干关系保持稳健,从而更好地实现概括化。我们提议在像素空间中显示信息,作为学习更尖锐的表示方式。通过学习只捕捉完成某项任务所需的最起码信息的面罩来显示信息。从直觉上看,我们的模型学会确定某项任务中哪些视觉提示真正重要。我们使用信号对音比的不同参数来锁定信息,这可以应用于网络中的任意值,例如:~在输入层制造像素。我们称之为InfoGating的方法,适用于多种目标,例如:多步前进和反向动态、Q-学习、行为克隆和标准的自我超强任务。我们的实验显示,学习确定和使用最起码的信息可以改进下游任务的概括化 -- 例如,基于Infoged图像的政策在转移/图像相关特性方面相当有力。</s>