@article{improvingvalueestimationcritically, title = {Improving Value Estimation Critically Enhances Vanilla Policy Gradient}, author = {Tao Wang and Ruipeng Zhang and Sicun Gao}, year = {2025}, eprint = {2505.19247}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2505.19247v1}, }