Publication:
BarlowRL: barlow twins for data-efficient reinforcement learning

Placeholder

Organizational Units

Program

KU Authors

Co-Authors

Advisor

Publication Date

2023

Language

en

Type

Conference proceeding

Journal Title

Journal ISSN

Volume Title

Abstract

This paper introduces BarlowRL, a data-efficient reinforcement learning agent that combines the Barlow Twins self-supervised learning framework with DER (Data-Efficient Rainbow) algorithm. BarlowRL outperforms both DER and its contrastive counterpart CURL on the Atari 100k benchmark. BarlowRL avoids dimensional collapse by enforcing information spread to the whole space. This helps RL algorithms to utilize uniformly spread state representation that eventually results in a remarkable performance. The integration of Barlow Twins with DER enhances data efficiency and achieves superior performance in the RL tasks. BarlowRL demonstrates the potential of incorporating self-supervised learning techniques, especially that of non-contrastive objectives, to improve RL algorithms.

Description

Source:

Asian Conference on Machine Learning Vol 222

Publisher:

JMLR-Jornal Machine Learning Research

Keywords:

Subject

Computer science, artificial intelligence, Computer science, theory and methods, Statistics and probability

Citation

Endorsement

Review

Supplemented By

Referenced By

Copy Rights Note

0

Views

0

Downloads