@article{proximalrankingpolicyoptimizationfor, title = {Proximal Ranking Policy Optimization for Practical Safety in Counterfactual Learning to Rank}, author = {Shashank Gupta and Harrie Oosterhuis and Maarten de Rijke}, year = {2024}, eprint = {2409.09881}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2409.09881v1}, }