Multi-Modal Imitation Learning from Unstructured Demonstrations using Generative Adversarial Nets
This addresses the scalability issue in robotics by enabling learning from messy, multi-task demonstrations, though it appears incremental as it builds on existing imitation learning and GAN methods.
The paper tackles the problem of scaling imitation learning to real-world scenarios by proposing a multi-modal framework that segments and imitates skills from unlabeled, unstructured demonstrations, achieving efficient skill separation and imitation with a single multi-modal policy in simulations.
Imitation learning has traditionally been applied to learn a single task from demonstrations thereof. The requirement of structured and isolated demonstrations limits the scalability of imitation learning approaches as they are difficult to apply to real-world scenarios, where robots have to be able to execute a multitude of tasks. In this paper, we propose a multi-modal imitation learning framework that is able to segment and imitate skills from unlabelled and unstructured demonstrations by learning skill segmentation and imitation learning jointly. The extensive simulation results indicate that our method can efficiently separate the demonstrations into individual skills and learn to imitate them using a single multi-modal policy. The video of our experiments is available at http://sites.google.com/view/nips17intentiongan