ROLL: Visual Self-Supervised Reinforcement Learning with Object Reasoning - Robotics Institute Carnegie Mellon University

ROLL: Visual Self-Supervised Reinforcement Learning with Object Reasoning

Yufei Wang, Gautham Narayan Narasimhan, Xingyu Lin, Brian Okorn, and David Held
Conference Paper, Proceedings of (CoRL) Conference on Robot Learning, November, 2020

Abstract

Current image-based reinforcement learning (RL) algorithms typically operate on the whole image without performing object-level reasoning. This leads to inefficient goal sampling and ineffective reward functions. In this paper, we improve upon previous visual self-supervised RL by incorporating object-level reasoning and occlusion reasoning. Specifically, we use unknown object segmentation to ignore distractors in the scene for better reward computation and goal generation; we further enable occlusion reasoning by employing a novel auxiliary loss and training scheme. We demonstrate that our proposed algorithm, ROLL (Reinforcement learning with Object Level Learning), learns dramatically faster and achieves better final performance compared with previous methods in several simulated visual control tasks. Project video and code are available at https://sites. google. com/andrew. cmu. edu/roll.

BibTeX

@conference{Wang-2020-126736,
author = {Yufei Wang and Gautham Narayan Narasimhan and Xingyu Lin and Brian Okorn and David Held},
title = {ROLL: Visual Self-Supervised Reinforcement Learning with Object Reasoning},
booktitle = {Proceedings of (CoRL) Conference on Robot Learning},
year = {2020},
month = {November},
}
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.