@article{optimizinglongtermvalueforauctionbased, title = {Optimizing Long-term Value for Auction-Based Recommender Systems via On-Policy Reinforcement Learning}, author = {Ruiyang Xu and Jalaj Bhandari and Dmytro Korenkevych and Fan Liu and Yuchen He and Alex Nikulkov and Zheqing Zhu}, year = {2023}, eprint = {2305.13747}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2305.13747v3}, }