Beyond Return Conditioning: Multi-Scale Sequence Modeling and Advantage-Guided Policy Routing for Offline RL.
Kunbao Wu|Xinning Zhu|Yang Qin|Tieru Wang|Jianzhou Diao|Zheng Hu
| Anthology ID: | DBLP:conf/cikm/WuZQWD025 |
|---|---|
| Volume: | Proceedings of the 34th ACM International Conference on Information and Knowledge Management, CIKM 2025, Seoul, Republic of Korea, November 10-14, 2025 |
| Year: | 2025 |
| Venue: | International Conference on Information and Knowledge Management (CIKM) |
| Publisher: | ACM |
| Pages: | 3396-3405 |
| URL: | https://doi.org/10.1145/3746252.3761116 |
| DOI: | https://doi.org/10.1145/3746252.3761116 |
| DBLP: | conf/cikm/WuZQWD025 |
| BibTeX: |
@inproceedings{wu-2025-beyond,
author = {Kunbao Wu and
Xinning Zhu and
Yang Qin and
Tieru Wang and
Jianzhou Diao and
Zheng Hu},
editor = {Meeyoung Cha and
Carl Yang and
Senjuti Basu Roy and
Chanyoung Park and
Zhenhui Jessie Li and
Noseong Park and
Carl Yang and
Senjuti Basu Roy and
Zhenhui Jessie Li and
Jaap Kamps and
Kijung Shin and
Bryan Hooi and
Lifang He},
title = {{Beyond Return Conditioning: Multi-Scale Sequence Modeling and Advantage-Guided Policy Routing for Offline RL}},
booktitle = {{Proceedings of the 34th ACM International Conference on Information and Knowledge Management, CIKM 2025, Seoul, Republic of Korea, November 10-14, 2025}},
pages = {3396--3405},
publisher = {ACM},
year = {2025},
url = {https://doi.org/10.1145/3746252.3761116},
doi = {https://doi.org/10.1145/3746252.3761116}
}