@article{momentsmatterstabilizingpolicyoptimizati, title = {Moments Matter:Stabilizing Policy Optimization using Return Distributions}, author = {Dennis Jabs and Aditya Mohan and Marius Lindauer}, year = {2026}, eprint = {2601.01803}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2601.01803}, }