Advantage-Conditioned Flow Policy for Offline Reinforcement Learning in Recommendation.

@inproceedings{eickhoff-2026-advantageconditioned, author = {Carsten Eickhoff and Xiaocong Chen and Carsten Eickhoff and Xiaocong Chen and Siyu Wang and Lina Yao and Xiaojie Yuan and Lina Yao and Xiaojie Yuan}, editor = {Hannah Bast and Alistair Moffat and Falk Scholer and Marc Najork and Min Zhang and Hannah Bast and Marc Najork and Min Zhang}, title = {{Advantage-Conditioned Flow Policy for Offline Reinforcement Learning in Recommendation}}, booktitle = {{Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2026, MelbourneVICAustralia, July 20-24, 2026}}, pages = {179--189}, publisher = {ACM}, year = {2026}, url = {https://doi.org/10.1145/3805712.3809626}, doi = {https://doi.org/10.1145/3805712.3809626} }