Learning Task Decomposition with Ordered Memory Policy Network

Yuchen Lu · Yikang Shen · Siyuan Zhou · Aaron Courville · Joshua B Tenenbaum · Chuang Gan

Keywords: [ Network Inductive Bias ] [ Hierarchical Imitation Learning ] [ Task Segmentation ]


Many complex real-world tasks are composed of several levels of subtasks. Humans leverage these hierarchical structures to accelerate the learning process and achieve better generalization. In this work, we study the inductive bias and propose Ordered Memory Policy Network (OMPN) to discover subtask hierarchy by learning from demonstration. The discovered subtask hierarchy could be used to perform task decomposition, recovering the subtask boundaries in an unstructured demonstration. Experiments on Craft and Dial demonstrate that our model can achieve higher task decomposition performance under both unsupervised and weakly supervised settings, comparing with strong baselines. OMPN can also be directly applied to partially observable environments and still achieve higher task decomposition performance. Our visualization further confirms that the subtask hierarchy can emerge in our model 1.

Chat is not available.