GloCAL: Glocalized Curriculum-Aided Learning of Multiple Tasks with Application to Robotic Grasping

TL;DR

GloCAL introduces a curriculum learning algorithm for robotic grasping that clusters tasks by performance, enabling efficient learning of multiple object grasps with higher success rates and less training time.

Contribution

The paper presents GloCAL, a novel curriculum learning method that clusters tasks and transfers global policies, improving multi-task robotic grasping efficiency and success.

Findings

GloCAL achieves 100% grasp success on 49 objects.

It outperforms other methods in efficiency, reducing training time.

GloCAL generalizes well across varied object complexities.

Abstract

The domain of robotics is challenging to apply deep reinforcement learning due to the need for large amounts of data and for ensuring safety during learning. Curriculum learning has shown good performance in terms of sample- efficient deep learning. In this paper, we propose an algorithm (named GloCAL) that creates a curriculum for an agent to learn multiple discrete tasks, based on clustering tasks according to their evaluation scores. From the highest-performing cluster, a global task representative of the cluster is identified for learning a global policy that transfers to subsequently formed new clusters, while the remaining tasks in the cluster are learned as local policies. The efficacy and efficiency of our GloCAL algorithm are compared with other approaches in the domain of grasp learning for 49 objects with varied object complexity and grasp difficulty from the EGAD! dataset. The results show that GloCAL is able to learn to grasp 100% of the objects, whereas other approaches achieve at most 86% despite being given 1.5 times longer training time.