论文标题
解开（联合国）可控功能
Disentangled (Un)Controllable Features
论文作者
论文摘要
在具有高维状态的MDP的背景下，下游任务主要应用于原始输入空间的压缩，低维表示。因此，已使用各种学习目标来获得有用的表示。但是，这些表示通常缺乏不同特征的解释性。我们提出了一种新颖的方法，该方法能够将潜在特征分解为可控和无法控制的分区。我们说明，在三种类型的环境上很容易解释所得的分区表示形式，并表明，在程序生成的迷宫环境的分布中，可以在孤立的可控制的潜在分区中采用计划算法是可行的。
In the context of MDPs with high-dimensional states, downstream tasks are predominantly applied on a compressed, low-dimensional representation of the original input space. A variety of learning objectives have therefore been used to attain useful representations. However, these representations usually lack interpretability of the different features. We present a novel approach that is able to disentangle latent features into a controllable and an uncontrollable partition. We illustrate that the resulting partitioned representations are easily interpretable on three types of environments and show that, in a distribution of procedurally generated maze environments, it is feasible to interpretably employ a planning algorithm in the isolated controllable latent partition.
