@article{cooperativemultiagentpolicygradientswith, title = {Cooperative Multi-Agent Policy Gradients with Sub-optimal Demonstration}, author = {Peixi Peng and Junliang Xing}, year = {2018}, eprint = {1812.01825}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/1812.01825v2}, }