Dibya Ghosh, Marlos C. Machado, Nicolas Le Roux. An operator view of policy gradient methods. In Hugo Larochelle, Marc'Aurelio Ranzato, Raia Hadsell, Maria-Florina Balcan, Hsuan-Tien Lin, editors, Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual. 2020. [doi]
@inproceedings{GhoshMR20, title = {An operator view of policy gradient methods}, author = {Dibya Ghosh and Marlos C. Machado and Nicolas Le Roux}, year = {2020}, url = {https://proceedings.neurips.cc/paper/2020/hash/22eda830d1051274a2581d6466c06e6c-Abstract.html}, researchr = {https://researchr.org/publication/GhoshMR20}, cites = {0}, citedby = {0}, booktitle = {Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual}, editor = {Hugo Larochelle and Marc'Aurelio Ranzato and Raia Hadsell and Maria-Florina Balcan and Hsuan-Tien Lin}, }