MILES: Making Imitation Learning Easy with Self-Supervision

Georgios Papagiannis, Edward Johns

Keywords: Imitation Learning, Robotic Manipulation, Self-Supervised Data Collection

TL;DR: MILES is an imitation learning method that collects data in a self-supervised manner to train policies that can learn complex manipulation skills from a single demonstration.

Abstract: Data collection in imitation learning often requires significant, laborious human supervision, such as numerous demonstrations and/or frequent environment resets for methods that incorporate reinforcement learning. In this work, we propose an alternative approach, MILES: a fully autonomous, self-supervised data collection paradigm and show that this enables efficient policy learning from just a single demonstration and a single environment reset. Our method, MILES, autonomously learns a policy for returning to and then following the single demonstration, whilst being self-guided during data collection, eliminating the need for additional human interventions. We evaluate MILES across several real-world tasks, including tasks that require precise contact-rich manipulation, and find that, under the constraints of a single demonstration and no repeated environment resetting, MILES significantly outperforms state-of-the-art alternatives like reinforcement learning and inverse reinforcement learning. Videos of our experiments, code, and supplementary material can be found on our website: https://sites.google.com/view/miles-imitation.

Submission Number: 31