@article{mbvimodelbasedvalueinitializationfor, title = {Optimal Control-Based Baseline for Guided Exploration in Policy Gradient Methods}, author = {Xubo Lyu and Site Li and Seth Siriya and Ye Pu and Mo Chen}, year = {2020}, eprint = {2011.02073}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2011.02073v5}, }