@article{learningtoexplorewithmetapolicygradient, title = {Learning to Explore with Meta-Policy Gradient}, author = {Tianbing Xu and Qiang Liu and Liang Zhao and Jian Peng}, year = {2018}, eprint = {1803.05044}, archivePrefix = {arXiv}, url = {http://arxiv.org/abs/1803.05044v2}, }