@article{apolicygradientmethodfortaskagnostic, title = {Task-Agnostic Exploration via Policy Gradient of a Non-Parametric State Entropy Estimate}, author = {Mirco Mutti and Lorenzo Pratissoli and Marcello Restelli}, year = {2020}, eprint = {2007.04640}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2007.04640v2}, }