@article{eepoexplorationenhancedpolicyoptimizatio, title = {EEPO: Exploration-Enhanced Policy Optimization via Sample-Then-Forget}, author = {Liang Chen and Xueting Han and Qizhou Wang and Bo Han and Jing Bai and Hinrich Schutze and Kam-Fai Wong}, year = {2025}, eprint = {2510.05837}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2510.05837}, }