MILES: Making Imitation Learning Easy with Self-Supervision

TL;DR

MILES introduces a fully autonomous, self-supervised imitation learning approach that efficiently learns policies from a single demonstration and environment reset, reducing human supervision and outperforming existing methods.

Contribution

The paper presents MILES, a novel self-supervised data collection paradigm enabling imitation learning with minimal demonstrations and no extra human intervention.

Findings

MILES outperforms state-of-the-art imitation learning methods.

Effective in contact-rich manipulation tasks like lock unlocking.

Operates efficiently with only one demonstration and environment reset.

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 we show that this enables efficient policy learning from just a single demonstration and a single environment reset. 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 evaluated MILES across several real-world tasks, including tasks that require precise contact-rich manipulation such as locking a lock with a key. We found that, under the constraints of a single demonstration and no repeated environment resetting, MILES significantly outperforms state-of-the-art alternatives like imitation learning methods that leverage reinforcement learning. Videos of our experiments and code can be found on our webpage: www.robot-learning.uk/miles.