Integrating Domain Knowledge for handling Limited Data in Offline RL

With the ability to learn from static datasets, Offline Reinforcement Learning (RL) emerges as a compelling avenue for real-world applications. However, state-of-the-art offline RL algorithms perform sub-optimally when confronted with limited data confined to specific regions within the state space....

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2024-06
Main Authors: Gangopadhyay, Briti, Wang, Zhao, Jia-Fong Yeh, Takamatsu, Shingo
Format: Article
Language:English
Subjects:
Algorithms
Datasets
Performance degradation
Regularization
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:With the ability to learn from static datasets, Offline Reinforcement Learning (RL) emerges as a compelling avenue for real-world applications. However, state-of-the-art offline RL algorithms perform sub-optimally when confronted with limited data confined to specific regions within the state space. The performance degradation is attributed to the inability of offline RL algorithms to learn appropriate actions for rare or unseen observations. This paper proposes a novel domain knowledge-based regularization technique and adaptively refines the initial domain knowledge to considerably boost performance in limited data with partially omitted states. The key insight is that the regularization term mitigates erroneous actions for sparse samples and unobserved states covered by domain knowledge. Empirical evaluations on standard discrete environment datasets demonstrate a substantial average performance increase of at least 27% compared to existing offline RL algorithms operating on limited data.
ISSN:2331-8422