SKILL-IL: Disentangling Skill and Knowledge in Multitask Imitation Learning
This work addresses the challenge of generalization in multitask imitation learning for robotics, offering a novel approach to improve efficiency and adaptability, though it is incremental in building on existing disentanglement concepts.
The paper tackled the problem of learning transferable content in multitask imitation learning by disentangling skill and knowledge in policy networks, resulting in a 30% improvement in task success rate over state-of-the-art methods across two environments and real robot navigation.
In this work, we introduce a new perspective for learning transferable content in multi-task imitation learning. Humans are able to transfer skills and knowledge. If we can cycle to work and drive to the store, we can also cycle to the store and drive to work. We take inspiration from this and hypothesize the latent memory of a policy network can be disentangled into two partitions. These contain either the knowledge of the environmental context for the task or the generalizable skill needed to solve the task. This allows improved training efficiency and better generalization over previously unseen combinations of skills in the same environment, and the same task in unseen environments. We used the proposed approach to train a disentangled agent for two different multi-task IL environments. In both cases we out-performed the SOTA by 30% in task success rate. We also demonstrated this for navigation on a real robot.