LGAICVROSep 14, 2017

One-Shot Visual Imitation Learning via Meta-Learning

arXiv:1709.04905v1616 citations
Originality Incremental advance
AI Analysis

This addresses the challenge of efficient skill acquisition for robots in unstructured environments, representing an incremental improvement over prior one-shot imitation methods.

The paper tackles the problem of enabling robots to quickly learn new skills from a single visual demonstration by introducing a meta-imitation learning method that scales to raw pixel inputs and reduces data requirements from prior tasks, achieving successful learning on simulated and real robots.

In order for a robot to be a generalist that can perform a wide range of jobs, it must be able to acquire a wide variety of skills quickly and efficiently in complex unstructured environments. High-capacity models such as deep neural networks can enable a robot to represent complex skills, but learning each skill from scratch then becomes infeasible. In this work, we present a meta-imitation learning method that enables a robot to learn how to learn more efficiently, allowing it to acquire new skills from just a single demonstration. Unlike prior methods for one-shot imitation, our method can scale to raw pixel inputs and requires data from significantly fewer prior tasks for effective learning of new skills. Our experiments on both simulated and real robot platforms demonstrate the ability to learn new tasks, end-to-end, from a single visual demonstration.

Code Implementations3 repos
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes