Temporal Representation Alignment: Successor Features Enable Emergent Compositionality in Robot Instruction Following
This addresses the challenge of enabling robots to perform compound tasks by composing learned basic steps, which is incremental as it builds on existing representation learning methods.
The paper tackled the problem of learning task representations that enable compositional generalization in robot instruction following, showing that a temporal alignment loss improves performance across diverse robotic manipulation tasks and simulations.
Effective task representations should facilitate compositionality, such that after learning a variety of basic tasks, an agent can perform compound tasks consisting of multiple steps simply by composing the representations of the constituent steps together. While this is conceptually simple and appealing, it is not clear how to automatically learn representations that enable this sort of compositionality. We show that learning to associate the representations of current and future states with a temporal alignment loss can improve compositional generalization, even in the absence of any explicit subtask planning or reinforcement learning. We evaluate our approach across diverse robotic manipulation tasks as well as in simulation, showing substantial improvements for tasks specified with either language or goal images.