Sparse-Reg: Improving Sample Complexity in Offline Reinforcement Learning using Sparsity

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Arnob, Samin Yeasar, Fujimoto, Scott, Precup, Doina
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912452714692608
author Arnob, Samin Yeasar
Fujimoto, Scott
Precup, Doina
author_facet Arnob, Samin Yeasar
Fujimoto, Scott
Precup, Doina
contents In this paper, we investigate the use of small datasets in the context of offline reinforcement learning (RL). While many common offline RL benchmarks employ datasets with over a million data points, many offline RL applications rely on considerably smaller datasets. We show that offline RL algorithms can overfit on small datasets, resulting in poor performance. To address this challenge, we introduce "Sparse-Reg": a regularization technique based on sparsity to mitigate overfitting in offline reinforcement learning, enabling effective learning in limited data settings and outperforming state-of-the-art baselines in continuous control.
format Preprint
id arxiv_https___arxiv_org_abs_2506_17155
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Sparse-Reg: Improving Sample Complexity in Offline Reinforcement Learning using Sparsity
Arnob, Samin Yeasar
Fujimoto, Scott
Precup, Doina
Machine Learning
Artificial Intelligence
In this paper, we investigate the use of small datasets in the context of offline reinforcement learning (RL). While many common offline RL benchmarks employ datasets with over a million data points, many offline RL applications rely on considerably smaller datasets. We show that offline RL algorithms can overfit on small datasets, resulting in poor performance. To address this challenge, we introduce "Sparse-Reg": a regularization technique based on sparsity to mitigate overfitting in offline reinforcement learning, enabling effective learning in limited data settings and outperforming state-of-the-art baselines in continuous control.
title Sparse-Reg: Improving Sample Complexity in Offline Reinforcement Learning using Sparsity
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2506.17155