The fitness of behaving agents depends on their knowledge of the environment, which demands efficient exploration strategies. Active sensing formalizes exploration as reduction of uncertainty about the current state of the environment. Despite strong theoretical justifications, active sensing has had limited applicability due to difficulty in estimating information gain. Here we address this issue by proposing a linear approximation to information gain and by implementing efficient gradient-based action selection within an artificial neural network setting. We compare information gain estimation with state of the art, and validate our model on an active sensing task based on MNIST dataset. We also propose an approximation that exploits the amortized inference network, and performs equally well in certain contexts.

行为代理的适应性取决于他们对环境的了解，这需要有效的探索策略。主动感知将探索形式化为减少对当前环境状态的不确定性。尽管有很强的理论依据，但由于难以估计信息增益，主动感知的适用性有限。在这里，我们通过提出信息增益的线性近似以及在人工神经网络设置中实施基于梯度的有效动作选择来解决这个问题。我们将信息增益估计与现有技术进行比较，并在基于 MNIST 数据集的主动传感任务上验证我们的模型。我们还提出了一种利用摊销推理网络的近似值，并且在某些情况下同样表现良好。