@inproceedings{NEURIPS2020_d1e7b08b, author = {Lorberbom, Guy and Maddison, Chris J and Heess, Nicolas and Hazan, Tamir and Tarlow, Daniel}, booktitle = {Advances in Neural Information Processing Systems}, editor = {H. Larochelle and M. Ranzato and R. Hadsell and M.F. Balcan and H. Lin}, pages = {18076--18086}, publisher = {Curran Associates, Inc.}, title = {Direct Policy Gradients: Direct Optimization of Policies in Discrete Action Spaces}, url = {https://proceedings.neurips.cc/paper_files/paper/2020/file/d1e7b08bdb7783ed4fb10abe92c22ffd-Paper.pdf}, volume = {33}, year = {2020} }