CASSL: Curriculum accelerated self-supervised learning

May 2018

CASSL: Curriculum accelerated self-supervised learning

Authors:

Adithya Murali, Lerrel Pinto, Dhiraj Gandhi, and Abhinav Gupta
Conference Paper
Proceedings of (ICRA) International Conference on Robotics and Automation

Abstract:

Recent self-supervised learning approaches focus on using a few thousand data points to learn policies for high-level, low-dimensional action spaces. However, scaling this framework for high-dimensional control require either scaling up the data collection efforts or using a clever sampling strategy for training. We present a novel approach - Curriculum Accelerated Self-Supervised Learning (CASSL) - to train policies that map visual information to high-level, higher- dimensional action spaces. CASSL orders the sampling of training data based on control dimensions: the learning and sampling are focused on few control parameters before other parameters. The right curriculum for learning is suggested by variance-based global sensitivity analysis of the control space. We apply our CASSL framework to learning how to grasp using an adaptive, underactuated multi-fingered gripper, a challenging system to control. Our experimental results indicate that CASSL provides significant improvement and generalization compared to baseline methods such as staged curriculum learning (8% increase) and complete end-to-end learning with random exploration (14% improvement) tested on a set of novel objects.
@conference{Murali-2018-113285,
author = {Adithya Murali And Lerrel Pinto And Dhiraj Gandhi And Abhinav Gupta},
title = {CASSL: Curriculum accelerated self-supervised learning},
booktitle = {Proceedings of (ICRA) International Conference on Robotics and Automation},
year = {2018},
month = {May},
pages = {6453 - 6460},
}
Copyright notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.