The Most Overestimated <i>Q</i> Value Regularization in High-Dimensional Discrete Action Spaces for Offline Reinforcement Learning

Seunghwan Yu, Homin Park, Byungjin Ko, Jisub Shin, Yoonki Hong, Taejoon Park, Jong-Wan Yoon

Open source

DOI
10.1109/tnnls.2025.3640101
Published
2026-06
Container
IEEE Transactions on Neural Networks and Learning Systems
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Open access
unknown

Credibility signals

uncertain Score 64/100 under policy 1.0.0. This is a metadata assessment, not a judgment of the paper's conclusions.

Show all credibility signals

Cite this work

BibTeX

@article{allodium:10.1109/tnnls.2025.3640101,
  title = {The Most Overestimated
                    <i>Q</i>
                    Value Regularization in High-Dimensional Discrete Action Spaces for Offline Reinforcement Learning},
  author = {Seunghwan Yu and Homin Park and Byungjin Ko and Jisub Shin and Yoonki Hong and Taejoon Park and Jong-Wan Yoon},
  year = {2026},
  journal = {IEEE Transactions on Neural Networks and Learning Systems},
  doi = {10.1109/tnnls.2025.3640101},
  url = {https://doi.org/10.1109/tnnls.2025.3640101}
}

RIS

TY  - JOUR
TI  - The Most Overestimated
                    <i>Q</i>
                    Value Regularization in High-Dimensional Discrete Action Spaces for Offline Reinforcement Learning
AU  - Seunghwan Yu
AU  - Homin Park
AU  - Byungjin Ko
AU  - Jisub Shin
AU  - Yoonki Hong
AU  - Taejoon Park
AU  - Jong-Wan Yoon
PY  - 2026
JO  - IEEE Transactions on Neural Networks and Learning Systems
DO  - 10.1109/tnnls.2025.3640101
UR  - https://doi.org/10.1109/tnnls.2025.3640101
ER  - 

APA

Yu, S., Park, H., Ko, B., Shin, J., Hong, Y., Park, T., & Yoon, J. (2026). The Most Overestimated <i>Q</i> Value Regularization in High-Dimensional Discrete Action Spaces for Offline Reinforcement Learning. IEEE Transactions on Neural Networks and Learning Systems. https://doi.org/10.1109/tnnls.2025.3640101

Source records