[Williams. "Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning." Machine Learning, 1992.](https://mlanthology.org/mlj/1992/williams1992mlj-simple/) doi:10.1007/BF00992696
@article{williams1992mlj-simple,
title = {{Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning}},
author = {Williams, Ronald J.},
journal = {Machine Learning},
year = {1992},
pages = {229-256},
doi = {10.1007/BF00992696},
volume = {8},
url = {https://mlanthology.org/mlj/1992/williams1992mlj-simple/}
}