A Statistical Guarantee for Representation Transfer in Multitask Imitation Learning
This work addresses sample efficiency for researchers and practitioners in imitation learning, offering a theoretical foundation for representation transfer, though it is incremental as it builds on existing multitask learning concepts.
The paper tackles the problem of sample efficiency in multitask imitation learning by providing a statistical guarantee that transferring representations from diverse source tasks improves learning on new tasks, with empirical validation showing that more source data enhances sample efficiency.
Transferring representation for multitask imitation learning has the potential to provide improved sample efficiency on learning new tasks, when compared to learning from scratch. In this work, we provide a statistical guarantee indicating that we can indeed achieve improved sample efficiency on the target task when a representation is trained using sufficiently diverse source tasks. Our theoretical results can be readily extended to account for commonly used neural network architectures with realistic assumptions. We conduct empirical analyses that align with our theoretical findings on four simulated environments$\unicode{x2014}$in particular leveraging more data from source tasks can improve sample efficiency on learning in the new task.