Exclusively Penalized Q-learning for Offline Reinforcement Learning

Constraint-based offline reinforcement learning (RL) involves policy constraints or imposing penalties on the value function to mitigate overestimation errors caused by distributional shift. This paper focuses on a limitation in existing offline RL methods with penalized value function, indicating t...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2024-10
Main Authors: Yeom, Junghyuk, Yonghyeon Jo, Kim, Jungmo, Lee, Sanghyeon, Han, Seungyul
Format: Article
Language:English
Subjects:
Bias
Control tasks
Errors
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Constraint-based offline reinforcement learning (RL) involves policy constraints or imposing penalties on the value function to mitigate overestimation errors caused by distributional shift. This paper focuses on a limitation in existing offline RL methods with penalized value function, indicating the potential for underestimation bias due to unnecessary bias introduced in the value function. To address this concern, we propose Exclusively Penalized Q-learning (EPQ), which reduces estimation bias in the value function by selectively penalizing states that are prone to inducing estimation errors. Numerical results show that our method significantly reduces underestimation bias and improves performance in various offline control tasks compared to other offline RL methods
ISSN:2331-8422