Discrete Task-Space Automatic Curriculum Learning for Robotic Grasping

Deep reinforcement learning algorithms struggle in the domain of robotics where data collection is time consuming and in some cases safety-constrained. For sample-efficiency, curriculum learning has shown good results in deep learning-based methods. However, the issue lies on the generation of the c...

Full description

Saved in:
Bibliographic Details
Main Authors: Kurkcu, Anil, Acar, Cihan, Campolo, Domenico, Tee, Keng Peng
Format: Conference Proceeding
Language:English
Subjects:
Automation
Curriculum Learning
Data collection
Deep Reinforcement Learning
Grasping
Learning systems
Measurement
Reinforcement learning
Robotic Grasping
Training
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Deep reinforcement learning algorithms struggle in the domain of robotics where data collection is time consuming and in some cases safety-constrained. For sample-efficiency, curriculum learning has shown good results in deep learning-based methods. However, the issue lies on the generation of the curriculum itself, which the field of automatic curriculum learning is trying to solve. We present an automatic curriculum learning algorithm for discrete task-space scenarios. Our curriculum generation is based on difficulty measure between tasks and learning progress metric within a task. We apply our algorithm to a grasp learning problem involving 49 diverse objects. Our results show that a policy trained based on a curriculum is both sample efficient compared to learning from scratch and able to learn tasks that the latter could not learn within a reasonable amount of time.
ISSN:2642-3901
DOI:10.23919/ICCAS52745.2021.9649917