Autonomous Curriculum Generation for Self-Learning Agents

Kurkcu, Anil; Campolo, Domenico; Tee, Keng Peng

doi:10.1109/icarcv50220.2020.9305338

Cited by 2 publications

(1 citation statement)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although curriculum learning is suitable for learning in a sample-efficient manner, the issue is about generating the curriculum itself. Automatic curriculum learning [18], [19] is a recent field of research aiming at developing algorithms that could autonomously organize the ordering of tasks in multi-task problem setups. The benefit is a sample-efficient training routine that would have not been possible if the tasks were ordered randomly during training.…”

Section: Introductionmentioning

confidence: 99%

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

Kurkcu,

Acar,

Campolo

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

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 sampleefficient 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 remaining tasks in the cluster are learnt 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× longer training time.

show abstract

Section: Introductionmentioning

confidence: 99%