Sujay Bhatt, Alec Koppel, Vikram Krishnamurthy. Policy Gradient using Weak Derivatives for Reinforcement Learning. In 58th IEEE Conference on Decision and Control, CDC 2019, Nice, France, December 11-13, 2019. pages 5531-5537, IEEE, 2019. [doi]
@inproceedings{BhattKK19-0, title = {Policy Gradient using Weak Derivatives for Reinforcement Learning}, author = {Sujay Bhatt and Alec Koppel and Vikram Krishnamurthy}, year = {2019}, doi = {10.1109/CDC40024.2019.9029403}, url = {https://doi.org/10.1109/CDC40024.2019.9029403}, researchr = {https://researchr.org/publication/BhattKK19-0}, cites = {0}, citedby = {0}, pages = {5531-5537}, booktitle = {58th IEEE Conference on Decision and Control, CDC 2019, Nice, France, December 11-13, 2019}, publisher = {IEEE}, }