@article{quantilerewardpolicyoptimizationalignmen, title = {Quantile Reward Policy Optimization: Alignment with Pointwise Regression and Exact Partition Functions}, author = {Simon Matrenok and Skander Moalla and Caglar Gulcehre}, year = {2025}, eprint = {2507.08068}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2507.08068}, }