Efficient Self-Supervised Data Collection for Offline Robot Learning
This addresses the challenge of data collection for complex robot tasks where manual policies are insufficient, though it is incremental as it builds on existing offline learning frameworks.
The paper tackles the problem of collecting diverse data for offline robot learning by proposing an active exploration method using goal-conditioned reinforcement learning, showing significant improvements in downstream tasks on simulated robot manipulation with visual inputs.
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.