BarlowRL: Barlow Twins for Data-Efficient Reinforcement Learning
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 to improve RL algorithms.
Cite
Text
Cagatan and Akgun. "BarlowRL: Barlow Twins for Data-Efficient Reinforcement Learning." Proceedings of the 15th Asian Conference on Machine Learning, 2023.Markdown
[Cagatan and Akgun. "BarlowRL: Barlow Twins for Data-Efficient Reinforcement Learning." Proceedings of the 15th Asian Conference on Machine Learning, 2023.](https://mlanthology.org/acml/2023/cagatan2023acml-barlowrl/)BibTeX
@inproceedings{cagatan2023acml-barlowrl,
title = {{BarlowRL: Barlow Twins for Data-Efficient Reinforcement Learning}},
author = {Cagatan, Omer Veysel and Akgun, Baris},
booktitle = {Proceedings of the 15th Asian Conference on Machine Learning},
year = {2023},
pages = {201-216},
volume = {222},
url = {https://mlanthology.org/acml/2023/cagatan2023acml-barlowrl/}
}