Efficient Self-Supervised Data Collection for Offline Robot Learning

TL;DR

This paper introduces an active, goal-conditioned reinforcement learning approach for collecting diverse robot interaction data, enhancing offline learning performance in complex manipulation tasks with visual inputs.

Contribution

It proposes a simple goal-conditioned RL method that actively explores to gather diverse data, improving offline robot learning for complex tasks.

Findings

Active data collection improves diversity of robot interaction data.

Enhanced data diversity leads to better downstream task performance.

Method outperforms passive data collection approaches in simulated experiments.

Abstract

A practical approach to robot reinforcement learning is to first collect a large batch of real or simulated robot interaction data, using some data collection policy, and then learn from this data to perform various tasks, using offline learning algorithms. Previous work focused on manually designing the data collection policy, and on tasks where suitable policies can easily be designed, such as random picking policies for collecting data about object grasping. For more complex tasks, however, it may be difficult to find a data collection policy that explores the environment effectively, and produces data that is diverse enough for the downstream task. In this work, we propose that data collection policies should actively explore the environment to collect diverse data. In particular, we develop a simple-yet-effective goal-conditioned reinforcement-learning method that actively focuses data collection on novel observations, thereby collecting a diverse data-set. We evaluate our method on simulated robot manipulation tasks with visual inputs and show that the improved diversity of active data collection leads to significant improvements in the downstream learning tasks.