@article{alyapunovanalysisofsoftmaxpolicygradient, title = {A Lyapunov Analysis of Softmax Policy Gradient for Stochastic Bandits}, author = {Tor Lattimore}, year = {2026}, eprint = {2603.26547}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2603.26547}, }