Multi-Modal Imitation Learning from Unstructured Demonstrations using Generative Adversarial Nets

TL;DR

This paper introduces a multi-modal imitation learning framework that can segment and imitate multiple skills from unstructured, unlabelled demonstrations using generative adversarial networks, enabling scalable learning of diverse tasks.

Contribution

It presents a novel joint skill segmentation and imitation learning method that handles unstructured demonstrations with a single multi-modal policy, improving scalability and applicability.

Findings

Efficiently segments demonstrations into individual skills.

Learns to imitate multiple skills with a single policy.

Effective in simulation for diverse task imitation.

Abstract

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